AI Model Catalog

Compare image, video, audio, and chat models before you spend credits

Browse 95+ AI models by task, input, output, provider, and credit notes. See what each model is good at, review real examples, then take your shortlist into Rivya for a real test.
6 signup credits
Quick signup
ImageVideoAudioChat

Model catalog

Find models by task, input, and output

Filter by modality, input type, provider, strengths, and credit notes. Open a model page to see real outputs, task fit, and a quick online trial.

4 model types

All models

Search by model, vendor, capability, or task. Then use the factual filters to narrow the page without opening every detail page.

95 model options

Compare input, output, credits, and example cues before you commit to a shortlist.

Compare model fit

Filter by fields Rivya already tracks for each model: modality and supported input. Task fit is shown on cards from the model content source.

Credits cue

Credit guidance is shown on every model card from the catalog content.

Modality

Supported input

95 model options

Compare input, output, credits, and example cues before you commit to a shortlist.

4 model typesAll

Good models to start with

Start here

Alibaba

Z-Image

Image

Alibaba's lightweight text-to-image model. Fast single-image generation with 5 aspect ratios — ideal for quick concept drafts and social media visuals at just 1 credit.

Why pick it

Lowest cost at 1 credit per generation

Best for
Cheap first-pass visual concepts
Input
Text
Output
Image
Credits
From 1 credit per generation
Fast single-image output for rapid iterationClean text-to-image with 5 aspect ratio presets

Google

Nano Banana

Image

Google's flexible image model for text-to-image and image-to-image with 11 aspect ratios, up to 10 reference images, and PNG/JPEG output. A strong fit for portraits, product compositions, and wider landing-page visuals.

Why pick it

11 aspect ratios including ultra-wide 21:9 and auto mode

Best for
Product compositions with multiple visual references
Input
Text / Reference / Image
Output
Image
Credits
From 3 credits per generation
Up to 10 reference images for guided creationPNG and JPEG output format options

Black Forest Labs

Flux 2 Pro

Image

Black Forest Labs' 32B-parameter flagship. Supports text-to-image and image-to-image with up to 8 reference images, 2K resolution, and accurate text rendering — built for product shots and brand visuals.

Why pick it

Up to 2K resolution with photorealistic textures

Best for
Product stills and ecommerce hero images
Input
Text / Reference / Image
Output
Image
Credits
From 5 credits per generation
Accurate text and logo rendering in imagesUp to 8 reference images for style/character consistency

OpenAI

GPT-5.5

Chat

OpenAI's advanced GPT chat model on Rivya for complex reasoning, image-aware analysis, research synthesis, and structured writing when the brief needs more room.

Why pick it

High ceiling for complex reasoning and multi-step analysis

Best for
Research synthesis across long or messy source packets
Input
Text
Output
Text / reasoning
Credits
Pay per use - credits based on usage
Supports image-aware chat with up to 6 imagesGood fit for structured briefs, research synthesis, and decision writing

OpenAI

GPT-5.4

Chat

OpenAI's higher-end AI chat model on Rivya, with stronger structured input handling, reasoning control, and tool-oriented conversation projects for more complex analysis and writing tasks.

Why pick it

Stronger complex analysis and multi-step planning

Best for
Long strategic briefs and decision memos
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Vision support with up to 6 imagesGood for structured tasks and tool-oriented conversations

OpenAI

GPT-5.4 Codex

Chat

OpenAI's higher-end Codex model on Rivya, with stronger coding, structured reasoning, and tool-oriented collaboration for demanding repo-scale development projects.

Why pick it

Higher-tier Codex reasoning and coding collaboration

Best for
Repo-scale debugging and architecture review
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Keeps the Responses projectGood for complex code, tool use, and multi-step technical work

OpenAI

GPT-5.3 Codex

Chat

OpenAI's latest and most capable Codex model on Rivya. It combines state-of-the-art code generation with deeper agentic reasoning for the most demanding development projects.

Why pick it

OpenAI's most capable code model

Best for
Hard debugging in large codebases
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
State-of-the-art code generation qualityDeepest reasoning for complex problems

OpenAI

GPT-5.2

Chat

OpenAI's flagship AI chat model on Rivya, with advanced reasoning, vision support for up to 6 images, and a 20K-character context window. It is a strong general GPT option for research, planning, writing, and image-aware analysis.

Why pick it

Advanced reasoning and complex analysis

Best for
Strategy memos and decision docs
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Vision support — analyze up to 6 images20K-character context window

OpenAI

GPT-5.2 Codex

Chat

OpenAI's more advanced Codex model on Rivya, with stronger reasoning for complex engineering tasks. It is optimized for long-horizon agentic coding, architecture decisions, and larger refactors where plain code generation is not enough.

Why pick it

Stronger reasoning for complex engineering

Best for
Architecture reviews and system design tradeoffs
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Best for system design and architecture12K output tokens for comprehensive code generation

OpenAI

GPT-5.1 Codex

Chat

OpenAI's upgraded Codex model on Rivya, with improved code accuracy and stronger reasoning for agentic coding tasks. It keeps the same long-output, repo-aware project while improving multi-file refactors and safer code edits.

Why pick it

Improved code accuracy over GPT-5 Codex

Best for
Multi-file refactors and migrations
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Better at multi-file refactoring12K output token limit for long code generation

OpenAI

GPT-5 Codex

Chat

OpenAI's code-specialized GPT-5 Codex model on Rivya for debugging, implementation planning, refactors, and technical problem-solving with vision support.

Why pick it

Code-specialized with 12K output token limit

Best for
Code review and bug fixing
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Optimized for code generation and debuggingVision support for analyzing screenshots/diagrams

Google

Gemini 3.1 Pro

Chat

Google's latest and most capable Gemini AI chat model on Rivya. With top-tier reasoning, vision, and instruction following, it is the strongest Gemini option for demanding analytical and creative tasks.

Why pick it

Google's most capable Gemini model

Best for
Long-context research packets and comparison work
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Top-tier reasoning and instruction followingVision support with up to 6 images

Google

Gemini 3 Pro

Chat

Google's higher-depth Gemini AI chat model on Rivya. With stronger reasoning than Gemini 2.5 Pro and vision support, it is better suited to research synthesis, technical writing, and more deliberate multimodal analysis.

Why pick it

Enhanced reasoning over Gemini 2.5 Pro

Best for
Long-form analysis and structured recommendations
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Vision support with up to 6 imagesStrong at research synthesis and technical writing

Google

Gemini 3 Flash

Chat

Google's next-gen fast AI chat model on Rivya. With even lower token costs than Gemini 2.5 Flash and stronger reasoning, it is built for high-volume multimodal chat, screenshot triage, and rapid assistant work.

Why pick it

Lowest token pricing among all chat models

Best for
Rapid multimodal triage and screenshot analysis
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Improved reasoning over Gemini 2.5 FlashVision support with up to 6 images

Google

Gemini 2.5 Pro

Chat

Google's more advanced Gemini AI chat model on Rivya. Stronger reasoning than Flash with vision support and 20K context, it is the better fit for research synthesis, document analysis, and structured writing at 2 credits.

Why pick it

Stronger reasoning than Gemini Flash

Best for
Research synthesis and analytical writeups
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Vision support — analyze up to 6 imagesBalanced cost at 2 credits per use

Google

Gemini 2.5 Flash

Chat

Google's fastest and most affordable AI chat model on Rivya. At 1 credit per use with vision support for up to 6 images, it fits quick Q&A, first-pass summaries, screenshot triage, and everyday AI assistance.

Why pick it

Lowest cost chat model at 1 credit

Best for
Fast research lookups and first-pass summaries
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Fast response for real-time conversationsVision support — analyze up to 6 images

Anthropic

Claude Opus 4.7

Chat

Anthropic's flagship Claude chat model on Rivya for deep reasoning, careful synthesis, executive writing, and high-impact text work.

Why pick it

Flagship-level text reasoning and synthesis

Best for
Executive memos and board-style narratives
Input
Text
Output
Text / reasoning
Credits
Pay per use - credits based on usage
Strong fit for long-form analysis and careful writingText-first Claude project in Rivya's current front end

Anthropic

Claude Opus 4.6

Chat

Anthropic's flagship Claude AI chat model on Rivya. It is built for deep reasoning, complex analysis, and high-quality writing in demanding, high-stakes projects.

Why pick it

Flagship reasoning and complex analysis

Best for
Executive memos and high-stakes narrative writing
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Higher ceiling for long-form understanding and output qualityText-first Claude project in Rivya's current front end

Anthropic

Claude Sonnet 4.6

Chat

Anthropic's balanced Claude AI chat model on Rivya. It keeps strong long-form reasoning and careful analysis for content, research, and coding projects without jumping to Opus-level spend.

Why pick it

Reliable reasoning with balanced quality

Best for
Reviewing long briefs, PRDs, and strategy docs
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Strong long-form understanding and multi-turn stabilityText-first Claude project in Rivya's current front end

Anthropic

Claude Opus 4.5

Chat

Anthropic's flagship Claude AI chat model on Rivya. It is exceptional at deep reasoning, complex analysis, and expert-level writing, making it a premium choice for mission-critical AI tasks.

Why pick it

Anthropic's most capable model

Best for
Deep research synthesis and difficult analysis
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Exceptional deep reasoning and complex analysisExpert-level writing and content quality

Anthropic

Claude Sonnet 4.5

Chat

Anthropic's balanced Claude AI chat model on Rivya. It is strong at nuanced writing, careful analysis, and safety-conscious responses, making it a strong Claude option for content creation and research.

Why pick it

Nuanced writing and careful analysis

Best for
Editorial rewrites and tone-sensitive writing
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Safety-conscious and well-calibrated responsesText-first Claude project in Rivya's current front end

Anthropic

Claude Haiku 4.5

Chat

Anthropic's lightweight Claude AI chat model on Rivya. It is tuned for speed, cost efficiency, and stable day-to-day chat performance in high-frequency projects where you want Claude tone without premium spend.

Why pick it

Better suited for low-latency, high-frequency use

Best for
Inbox triage and quick internal Q&A
Input
Text
Output
Text / reasoning
Credits
Pay per use — credits based on usage
Much cheaper token pricing than Sonnet or OpusText-first Claude project in Rivya's current front end

Alibaba

Z-Image

Image

Alibaba's lightweight text-to-image model. Fast single-image generation with 5 aspect ratios — ideal for quick concept drafts and social media visuals at just 1 credit.

Why pick it

Lowest cost at 1 credit per generation

Best for
Cheap first-pass visual concepts
Input
Text
Output
Image
Credits
From 1 credit per generation
Fast single-image output for rapid iterationClean text-to-image with 5 aspect ratio presets

Google

Nano Banana 2

Image

Google's next-gen image model with 4K resolution, 15 aspect ratios (including extreme 8:1), Google Search grounding, and up to 14 reference images — the most flexible image generator on Rivya.

Why pick it

Up to 4K resolution (1K / 2K / 4K selectable)

Best for
Large-format image concepts and panorama-style layouts
Input
Text / Reference / Image
Output
Image
Credits
From 5 credits per generation
15 aspect ratios including extreme 8:1 and 1:8 panoramicGoogle Search grounding for real-world context

Google

Nano Banana Pro

Image

Google's premium image model with 4K output, 11 aspect ratios, and up to 8 reference images. Optimized for high-fidelity brand and campaign visuals with superior detail and color accuracy.

Why pick it

Up to 4K resolution with enhanced fidelity

Best for
Premium brand visuals and higher-end marketing images
Input
Text / Reference / Image
Output
Image
Credits
From 8 credits per generation
11 aspect ratios with auto-detect optionUp to 8 reference images for brand consistency

Google

Nano Banana

Image

Google's flexible image model for text-to-image and image-to-image with 11 aspect ratios, up to 10 reference images, and PNG/JPEG output. A strong fit for portraits, product compositions, and wider landing-page visuals.

Why pick it

11 aspect ratios including ultra-wide 21:9 and auto mode

Best for
Product compositions with multiple visual references
Input
Text / Reference / Image
Output
Image
Credits
From 3 credits per generation
Up to 10 reference images for guided creationPNG and JPEG output format options

OpenAI

GPT Image 2

Image

OpenAI's newer GPT Image model on Rivya, with text-to-image, image-to-image, up to 16 reference images, and clear 1K / 2K / 4K credit tiers.

Why pick it

Text-to-image and image-to-image in one Rivya model page

Best for
High-resolution product and campaign visuals
Input
Text / Reference / Image
Output
Image
Credits
From 3 credits per generation
1K, 2K, and 4K resolution tiers for clearer budget controlUp to 16 reference images for structured editing briefs

OpenAI

GPT Image 1.5

Image

OpenAI's image model with medium/high quality tiers and up to 16 reference images. Excels at following complex instructions and rendering coherent scenes with accurate spatial relationships.

Why pick it

Up to 16 reference images — highest on Rivya

Best for
Instruction-heavy product and campaign visuals
Input
Text / Reference / Image
Output
Image
Credits
From 4 credits per generation
Medium and High quality tiers for cost controlSuperior prompt comprehension from OpenAI's language model

OpenAI

4o Image

Image

OpenAI's 4o Image model is now available as a dedicated text-to-image path on Rivya. It keeps the page setup intentionally narrow for now: prompt plus 3 supported aspect ratios at a fixed 3 credits per image.

Why pick it

Dedicated OpenAI 4o Image entry instead of folding into another model

Best for
Quick concept visuals from a text brief
Input
Text
Output
Image
Credits
From 3 credits per generation
Text-to-image flow with the listed 3 credits per image pathThree documented aspect ratio options: 1:1, 3:2, and 2:3

ByteDance

Seedream 5.0 Lite

Image

ByteDance's lighter Seedream image model with shared pricing across text-to-image and image editing. It supports 8 aspect ratios, up to 14 reference images, and currently costs 6 credits per run.

Why pick it

Fixed 6-credit pricing for both text-to-image and image-to-image

Best for
Reference-heavy campaign boards and mood directions
Input
Text / Reference / Image
Output
Image
Credits
From 6 credits per generation
Up to 14 reference images for guided editing projects8 aspect ratios including ultra-wide 21:9

ByteDance

Seedream 4.5

Image

ByteDance's high-end image model with 2K/4K quality tiers, 8 aspect ratios, and up to 14 reference images. Known for cinematic color grading and rich texture detail in fashion and lifestyle visuals.

Why pick it

Selectable 2K (Basic) and 4K (High) quality tiers

Best for
Fashion and lifestyle campaign images
Input
Text / Reference / Image
Output
Image
Credits
From 7 credits per generation
Up to 14 reference images for guided creation8 aspect ratios including ultra-wide 21:9

ByteDance

Seedream 4.0

Image

Seedream 4.0 is a balanced ByteDance image model on Rivya for text-to-image generation, reference-image editing, and explicit output controls.

Why pick it

One model slot covers both text-to-image and image editing

Best for
Lifestyle visuals and editorial-style image drafts
Input
Text / Reference / Image
Output
Image
Credits
Fixed 6 credits per generation
Keeps the public `image_resolution` and `max_images` controls visibleSupports up to 10 reference images for the edit path

ByteDance

Seedream 3.0

Image

Seedream 3.0 now returns as a standalone legacy image model on Rivya. It currently keeps only the public text-to-image path and costs 5 credits per run.

Why pick it

Keeps Seedream 3.0 available as its own legacy text-to-image entry

Best for
Teams that want to preserve an older Seedream visual direction
Input
Text
Output
Image
Credits
Fixed 5 credits per generation
Exposes only the parameter subset that the public docs clearly showLighter parameter surface than newer Seedream options

xAI

Grok Imagine

Image

xAI's image model with strong creative interpretation and 5 aspect ratios. Single-image generation focused on artistic expression and unconventional visual styles.

Why pick it

Strong creative and artistic interpretation

Best for
Bold concept visuals and experimental art direction
Input
Text / Reference / Image
Output
Image
Credits
From 4 credits per generation
Unique visual styles distinct from other modelsText-to-image and image-to-image support

Black Forest Labs

Flux 2 Pro

Image

Black Forest Labs' 32B-parameter flagship. Supports text-to-image and image-to-image with up to 8 reference images, 2K resolution, and accurate text rendering — built for product shots and brand visuals.

Why pick it

Up to 2K resolution with photorealistic textures

Best for
Product stills and ecommerce hero images
Input
Text / Reference / Image
Output
Image
Credits
From 5 credits per generation
Accurate text and logo rendering in imagesUp to 8 reference images for style/character consistency

Black Forest Labs

Flux 2 Flex

Image

Flux 2 family's editing-focused variant. Specializes in structural adjustments and style transfer with up to 8 reference images and 2K resolution — ideal for iterating on existing visuals.

Why pick it

Optimized for image editing and style transfer

Best for
Editing an existing campaign or product image
Input
Text / Reference / Image
Output
Image
Credits
From 14 credits per generation
Up to 8 reference images for guided edits2K resolution output with Flux 2 quality

Black Forest Labs

Flux Kontext Max

Image

Black Forest Labs' enhanced Flux Kontext model for more demanding prompt-led generation and image editing tasks. Rivya currently keeps both text-to-image and image-to-image on the same async project and prices them at a fixed 8 credits per run under the platform's current policy.

Why pick it

Fixed 8-credit pricing for both generation and editing on Rivya

Best for
Key visual refinements on an important campaign still
Input
Text / Reference / Image
Output
Image
Credits
From 8 credits per generation
Higher-end Kontext tier for harder prompt or edit tasksOne-model project for text-to-image and one-image editing

Black Forest Labs

Flux Kontext Pro

Image

Black Forest Labs' lower-cost Flux Kontext project for text-to-image and single-image editing. Rivya currently exposes both text-to-image and image-to-image on the same async image project, with fixed 4-credit pricing for both modes under the current platform pricing policy.

Why pick it

Fixed 4-credit pricing for both generation and editing on Rivya

Best for
Ad and social variants from one approved source image
Input
Text / Reference / Image
Output
Image
Credits
From 4 credits per generation
One-model project for text-to-image and one-image editingBuilt-in translation switch for the English-only prompt requirement

Alibaba

Qwen2 Image

Image

Alibaba's Qwen2 image model is currently integrated on Rivya as one fixed-price image project. It safely covers text-to-image and image-to-image with the shared aspect-ratio subset both public docs expose, plus PNG/JPEG output, seed reuse, and a simple NSFW switch.

Why pick it

Fixed 6-credit pricing for both text-to-image and image-to-image

Best for
Chinese-language posters and campaign visuals
Input
Text / Reference / Image
Output
Image
Credits
From 6 credits per generation
Uses `qwen2/text-to-image` for text runs and `qwen2/image-edit` for reference-image runsShared safe aspect-ratio subset across both public Qwen2 docs

Alibaba

Qwen Image

Image

Alibaba Qwen family's image model with HD presets (Square, Portrait, Landscape) and PNG/JPEG output. Strong at Chinese-language prompts and culturally nuanced visual generation.

Why pick it

HD preset sizes: Square, Portrait 4:3/16:9, Landscape 4:3/16:9

Best for
Chinese-language marketing visuals
Input
Text / Reference / Image
Output
Image
Credits
From 4 credits per generation
Strong Chinese-language prompt understandingPNG and JPEG output format options

Midjourney

Midjourney

Image

Midjourney's V7 image model for text-to-image and image-to-image with Niji anime modes, 3 speed tiers (Relaxed/Fast/Turbo), style references, and Omni Reference-driven consistency. Still the benchmark for cinematic art, illustrations, and moodboards.

Why pick it

Unmatched aesthetic quality — the industry benchmark

Best for
Cinematic concept art and moodboards
Input
Text / Reference / Image
Output
Image
Credits
From 3 credits per generation
V7 + V6.1 + V6 + Niji 7/6 anime modes3 speed tiers: Relaxed, Fast, Turbo

Recraft

Recraft Remove Background

Image

Recraft's background-removal model on Rivya for isolating the subject from one existing image. Use it when the next step needs a transparent asset, a clean cutout, or a source image without the original background.

Why pick it

Single-purpose cutout tool with fixed 1-credit pricing

Best for
Removing the background from one product, portrait, or catalog image before design work
Input
Reference / Image
Output
Image
Credits
From 1 credit per generation
Built for one uploaded image and usually needs no prompt at allStrong fit for product photos, portraits, and other assets with readable subject edges

Recraft

Recraft Crisp Upscale

Image

Recraft's light image-upscaling model on Rivya for low-cost sharpness and clarity boosts on one approved still. Use it when the chosen image only needs a cheap polish pass before export, not a heavier delivery-grade upscale.

Why pick it

Fixed 1-credit cleanup pass for one uploaded image

Best for
Giving one thumbnail, social graphic, or small product image a quick clarity lift
Input
Reference / Image
Output
Image
Credits
From 1 credit per generation
Good for quick sharpness and light enlargement before publishing or handoffNo required prompt and no size ladder to manage, so it stays useful as a low-friction precheck

Alibaba

Wan 2.7 Image Pro

Image

Alibaba's higher-end Wan 2.7 image model, currently exposed on Rivya as a separate image slot for text-to-image and image editing. Pricing stays fixed at 12 credits per run by explicitly keeping generation to a single output image.

Why pick it

Fixed 12-credit pricing for both text-to-image and image-to-image

Best for
Brand key visuals and launch campaign stills
Input
Text / Reference / Image
Output
Image
Credits
From 12 credits per generation
Up to 9 reference images for guided editing projectsShared Wan 2.7 image family with a clearer premium tier

Alibaba

Wan 2.7 Image

Image

Alibaba's standard Wan 2.7 image model is exposed on Rivya as its own image slot for text-to-image and image editing, and currently costs 5 credits per run.

Why pick it

Currently costs 5 credits per run

Best for
Multi-reference social and campaign draft boards
Input
Text / Reference / Image
Output
Image
Credits
From 5 credits per generation
Supports both text-to-image and image-to-imageUp to 9 reference images for guided edits

Google

Google Imagen4 Ultra

Image

Google Imagen4 Ultra is Rivya's premium Imagen text-to-image tier. It is currently integrated as a fixed 12-credit, single-image project with public prompt, negative prompt, aspect ratio, and seed controls.

Why pick it

Fixed 12-credit pricing on Rivya

Best for
Homepage hero art and premium campaign visuals
Input
Text
Output
Image
Credits
From 12 credits per generation
Premium Google Imagen text-to-image tierNegative prompt, aspect ratio, and seed controls

Google

Google Imagen4

Image

Google Imagen4 is Rivya's standard Imagen text-to-image tier. It is currently integrated as a fixed 8-credit, single-image project with public prompt, negative prompt, aspect ratio, and seed controls.

Why pick it

Fixed 8-credit pricing on Rivya

Best for
Website hero graphics and editorial illustrations
Input
Text
Output
Image
Credits
From 8 credits per generation
Standard Google Imagen text-to-image tierNegative prompt, aspect ratio, and seed controls

Google

Google Imagen4 Fast

Image

Google Imagen4 Fast is Rivya's lightweight Imagen text-to-image tier. It currently keeps a single-image project, uses fixed 4-credit pricing, and exposes the public prompt, negative prompt, aspect ratio, and seed controls without opening multi-image output.

Why pick it

Fixed 4-credit pricing on Rivya

Best for
Fast landing-page or blog visual directions
Input
Text
Output
Image
Credits
From 4 credits per generation
Lightweight Google Imagen text-to-image entryNegative prompt, aspect ratio, and seed controls

Topaz

Topaz Image Upscaler

Image

Topaz's delivery-grade image upscaler on Rivya for approved stills that need a real size jump. Use it when the composition is already final and the remaining problem is export resolution, review size, or print readiness.

Why pick it

Made for approved stills that need a real delivery-size jump, not a regenerated composition

Best for
Upscaling approved ecommerce, product, or campaign stills for larger delivery formats
Input
Reference / Image
Output
Image
Credits
From 5 credits per run
Explicit UI ladder built on factor 1, 2, 4, and 8 keeps size-versus-cost tradeoffs easy to chooseStronger fit than Recraft Crisp Upscale when the chosen still is already final and output size actually matters

Ideogram

Ideogram V3

Image

Ideogram V3 is Rivya's text-to-image model for text rendering, poster layouts, and design-first image prompts. Current pricing is 4 credits for TURBO, 7 for BALANCED, and 10 for QUALITY.

Why pick it

Rendering-speed tiers: TURBO, BALANCED, QUALITY

Best for
Poster concepts and title-led ad graphics
Input
Text
Output
Image
Credits
From 4 credits per generation
Design-oriented Ideogram V3 image generationMagicPrompt expansion toggle

Ideogram

Ideogram V3 Reframe

Image

Ideogram V3 Reframe is currently integrated on Rivya as a single-image reframing project with rendering-speed pricing. Current pricing is 4 credits for TURBO, 7 for BALANCED, and 10 for QUALITY.

Why pick it

Rendering-speed tiers: TURBO, BALANCED, QUALITY

Best for
Adapting one approved visual to new aspect ratios
Input
Reference / Image
Output
Image
Credits
From 4 credits per generation
Single-image reframing projectPrompt is optional for this model

Ideogram

Ideogram V3 Remix

Image

Ideogram V3 Remix is currently integrated on Rivya as a single-image remix project with rendering-speed pricing. Current pricing is 4 credits for TURBO, 7 for BALANCED, and 10 for QUALITY.

Why pick it

Rendering-speed tiers: TURBO, BALANCED, QUALITY

Best for
Alternative art directions from one source image
Input
Text / Reference / Image
Output
Image
Credits
From 4 credits per generation
Single-image remix projectMagicPrompt, strength, and negative prompt controls

Ideogram

Ideogram Character

Image

Character-consistency option for turning one approved character image into new scenes, outfits, and formats. Use it when identity retention matters more than broad image editing and you only need one output image at a time.

Why pick it

Single-reference project tuned for keeping one character recognizable across new scenes

Best for
Keeping one mascot, avatar, or illustrated character recognizable across many new scenes
Input
Text / Reference / Image
Output
Image
Credits
From 12 credits per generation
Separated from Ideogram V3, Reframe, and Remix so users can choose consistency over broader editing freedomPredictable one-image output with TURBO, BALANCED, and QUALITY credit tiers

ByteDance

Seedance 2.0

Video

ByteDance's full Seedance 2.0 video model with explicit support for prompt-only generation, frame-driven animation, and multimodal reference generation. Rivya keeps the documented role split explicit so frame inputs and multimodal references stay mutually exclusive instead of collapsing into one ambiguous upload bucket.

Why pick it

Full Seedance 2.0 scene split: text, frames, and multimodal reference

Best for
Higher-quality short videos from prompts, frames, or reference bundles
Input
Text
Output
Video
Credits
From 64 credits per run
Prompt-led, frame-led, and multimodal reference projects in one model480p and 720p output with adaptive aspect ratio support

ByteDance

Seedance 2.0 Fast

Video

ByteDance's faster Seedance 2.0 video model with full scene routing for prompt-only generation, frame-driven image animation, and multimodal reference video generation. Rivya keeps the documented scene split explicit so first/last-frame inputs do not collide with reference image, video, and audio roles.

Why pick it

Full Seedance 2.0 Fast scene split: text, frames, and multimodal reference

Best for
Fast ad previs from prompts or storyboard frames
Input
Text
Output
Video
Credits
From 52 credits per run
480p and 720p output with adaptive aspect ratio supportOptional synced audio generation and final-frame return

ByteDance

Seedance 1.5 Pro

Video

ByteDance's flagship video model for text-to-video and image-to-video with native audio-visual sync. 480p–1080p, 4–12s clips, 6 aspect ratios, dynamic/fixed lens control, optional audio generation, and lip-sync support.

Why pick it

Native audio-visual sync with precise lip-sync

Best for
Short clips with synced dialogue and motion
Input
Text / Reference / Image
Output
Video
Credits
From 28 credits per generation
480p / 720p / 1080p resolution options4s, 8s, or 12s configurable clip duration

ByteDance

Seedance 1.0 Pro

Video

ByteDance's Seedance 1.0 Pro model, exposed on Rivya as the standard 1.0 Pro option for both text-to-video and image-to-video. It keeps the current page setup aligned to the public V1 Pro docs with resolution, duration, camera lock, seed, and safety-check controls.

Why pick it

Supports both text-to-video and image-to-video

Best for
Short cinematic clips
Input
Text / Reference / Image
Output
Video
Credits
From 25 credits per generation
480p, 720p, and 1080p output tiers5s and 10s duration controls

ByteDance

Seedance 1.0 Pro Fast

Video

ByteDance's fast image-to-video model. Animates a single reference image into 5s or 10s clips at 720p/1080p — optimized for speed when you need quick video from a still.

Why pick it

Image-to-video specialist — fast turnaround

Best for
Fast still-to-video animation
Input
Text / Reference / Image
Output
Video
Credits
16-72 credits per generation
720p and 1080p resolution options5s or 10s clip duration

ByteDance

Seedance 1.0 Lite

Video

ByteDance's Seedance 1.0 Lite model is exposed on Rivya as the lighter 1.0 option for both text-to-video and image-to-video. It follows the public V1 Lite parameter set and currently uses a lower pricing ladder than Seedance 1.0 Pro.

Why pick it

Supports both text-to-video and image-to-video

Best for
Lower-cost storyboard tests
Input
Text / Reference / Image
Output
Video
Credits
From 16 credits per generation
Lower pricing than Seedance 1.0 ProOptional second image as an end frame in image-to-video mode

HappyHorse

HappyHorse 1.0

Video

A flexible AI video model on Rivya for text-to-video, single-image motion, multi-image reference video, and video editing from one public model page.

Why pick it

One model page covers text, image, reference, and video-edit workflows

Best for
Short ad or product motion drafts from a written brief
Input
Text / Reference / Image / Video
Output
Video
Credits
From 28 credits per generation
Supports 720p and 1080p fixed-price output tiersAccepts up to 9 image references when no video is attached

Alibaba

Wan 2.7 Video

Video

Alibaba's newer Wan video line with pricing by resolution and duration. Rivya currently exposes text-to-video, image-to-video, and video editing in one model slot, starting at 80 credits per generation.

Why pick it

Resolution and duration pricing: 720p = 16 credits/sec, 1080p = 24 credits/sec

Best for
Short-form product promos and social cutdowns
Input
Text / Reference / Image / Video
Output
Video
Credits
From 80 credits per generation
Supports text-to-video, image-to-video, and video editing in one model slotImage-to-video can use one image or a first-and-last-frame pair

Alibaba

Wan 2.6

Video

Alibaba's triple-mode Wan option on Rivya: text-to-video, image-to-video, and source-video editing in one project. It supports 720p/1080p, 5–15 second clips, and one image or one source video at a time.

Why pick it

Triple mode: text-to-video + image-to-video + video-to-video

Best for
Video-to-video edits from an existing source clip
Input
Text / Reference / Image / Video
Output
Video
Credits
From 70 credits per generation
One heavy Wan option that can start from a source video instead of only text or still imagesOne image or one source video keeps the edit path explicit

Alibaba

Wan 2.5 Video

Video

Wan 2.5 is now exposed on Rivya as one shared entry for text-to-video and image-to-video. Current pricing is `720p_5 = 60`, `720p_10 = 120`, `1080p_5 = 100`, and `1080p_10 = 200` credits.

Why pick it

One model slot for both text-to-video and image-to-video

Best for
5 or 10 second Wan promo clips from text or one hero image
Input
Text / Reference / Image
Output
Video
Credits
From 60 credits per generation
Pricing follows four visible resolution and duration tiersKeeps the existing async video result chain without a new result type

Alibaba

Wan 2.2 A14B Turbo

Video

Wan 2.2 A14B Turbo now covers text-to-video, image-to-video, plus an image-and-audio-driven video path on Rivya. Current pricing is `480p = 8` and `720p = 12` for text or image runs, plus `480p = 16`, `580p = 20`, and `720p = 24` when one image and one audio clip drive the result.

Why pick it

One model slot now covers text, image, and image-plus-audio-driven video generation

Best for
Lighter Wan text-to-video experiments
Input
Text / Reference / Image / Audio
Output
Video
Credits
From 8 credits per generation
Business pricing stays tiered between lighter text-image runs and heavier image-plus-audio-driven runsThe image-plus-audio-driven path keeps its own advanced parameter subset instead of collapsing everything to defaults

Alibaba

Wan Animate Replace

Video

Wan's character-replacement video model on Rivya for swapping who appears in an existing clip. Use one public source video URL, one public replacement image URL, and a resolution tier when the motion is already right and the visible subject needs to change.

Why pick it

Keeps the public `video_url + image_url + resolution` shape instead of inventing a prompt-heavy project

Best for
Replacing the on-screen subject or character while keeping the source clip's motion
Input
Video
Output
Video
Credits
From 12 credits per generation
Best suited to subject or character swaps where the original motion should stay intactWorks well when both assets already live on public storage and can be fetched upstream

MiniMax

Hailuo 2.3

Video

MiniMax's image-to-video model with Standard/Pro quality tiers, 768P/1080P resolution, and 6s or 10s clips. Known for smoother motion and natural transitions from still images.

Why pick it

Standard and Pro quality tiers

Best for
Animating portrait or fashion stills into motion
Input
Text / Reference / Image
Output
Video
Credits
From 25 credits per generation
768P and 1080P resolution options6s or 10s configurable clip duration

MiniMax

Hailuo Pro

Video

MiniMax's older Hailuo Pro video model is connected here as one fixed Pro-tier model for both text-to-video and image-to-video. Image mode accepts 1 or 2 reference images, with the second image used as the last frame, and each run currently costs 57 credits.

Why pick it

One model for both text-to-video and image-to-video

Best for
Higher-quality motion drafts from one key visual
Input
Text / Reference / Image
Output
Video
Credits
57 credits per generation
Image mode supports a first frame or a first-and-last-frame pairConnected on the publicly confirmed fixed Pro tier

MiniMax

Hailuo Standard

Video

MiniMax's older Hailuo Standard video model, unified here as one model for both text-to-video and image-to-video. Image mode accepts 1 or 2 reference images, with the second image used as the last frame, and the currently verified public pricing tiers range from 12 to 50 credits.

Why pick it

One model for both text-to-video and image-to-video

Best for
Turning one hero still into a short motion teaser
Input
Text / Reference / Image
Output
Video
Credits
12-50 credits per generation
Image mode supports a first frame or a first-and-last-frame pair512P and 768P image-driven tiers

Kuaishou

Kling 3.0

Video

Kuaishou's premium video model for text-to-video and image-to-video, with Standard (720P) / Pro (1080P) tiers, single or multi-shot structure, 3–15s duration, optional audio generation, and up to 2 reference images.

Why pick it

Standard (720P) and Pro (1080P) quality tiers

Best for
Storyboard-style ad previs with explicit shot planning
Input
Text / Reference / Image
Output
Video
Credits
From 42 credits per generation
Single-shot or multi-shot generation modesFlexible 3–15 second clip duration

Kuaishou

Kling 3.0 motion-control

Video

Newer Kling motion-control option for driving one subject from one reference image plus one motion video, with explicit background-source choice. Use it when you want motion transfer plus stronger control over whether the scene should come from the video or the image.

Why pick it

Exact 1-image + 1-motion-video project keeps identity and movement roles clear

Best for
Motion-transfer runs where you need to choose whether the background comes from the motion video or the reference image
Input
Text / Reference / Image / Video
Output
Video
Credits
From 20 credits per generation
Adds `background_source` on top of character orientation, which is the main upgrade over Kling 2.6 motion-controlFixed Standard (720P) and Pro (1080P) pricing at 20 / 27 credits

Kuaishou

Kling 2.6

Video

Kuaishou's video model with optional audio generation, 5s/10s clips, and 3 aspect ratios. Strong at human motion and expressive character animation with natural physics.

Why pick it

Optional audio generation with video

Best for
Character performance and expressive movement
Input
Text / Reference / Image
Output
Video
Credits
From 55 credits per generation
5s or 10s clip duration3 aspect ratios: 1:1, 16:9, 9:16

Kuaishou

Kling 2.6 motion-control

Video

Dedicated motion-transfer project for driving one subject from one reference image plus one motion video. Use it when you want a cheaper Kling motion-control pass and can live without the extra scene controls in Kling 3.0 motion-control.

Why pick it

Exact 1-image + 1-motion-video project, so it is clear what drives identity and what drives movement

Best for
Driving one character from a still image plus a separate motion-reference clip
Input
Text / Reference / Image / Video
Output
Video
Credits
From 16 credits per generation
Cheaper entry point than Kling 3.0 motion-control at 16 / 22 creditsOptional prompt lets the uploaded motion clip stay primary

Kuaishou

Kling V2.5 Turbo Pro

Video

Kuaishou's Kling V2.5 Turbo Pro video model, now supporting both text-to-video and image-to-video. Public pricing evidence clearly covers both text and image tiers at 5 seconds and 10 seconds, so Rivya maps it directly to 42 / 84 credits.

Why pick it

Clear public price evidence for both text and image tiers

Best for
Short ad previs from text or first-and-tail frames
Input
Text / Reference / Image
Output
Video
Credits
42-84 credits per generation
Text and image generation share one aligned model entryImage mode supports a first frame plus an optional tail frame

Kuaishou

Kling V2.1 Master

Video

Kuaishou's older Kling V2.1 Master video model now supports both text-to-video and image-to-video on Rivya. Current pricing is 160 credits for 5 seconds and 320 credits for 10 seconds.

Why pick it

Fixed 5-second and 10-second price tiers

Best for
Legacy Kling Master comparisons against newer tiers
Input
Text / Reference / Image
Output
Video
Credits
160-320 credits per generation
Text and image generation now share one aligned model entryText keeps `aspect_ratio` while image stays on doc-backed fields only

Kuaishou

Kling V2.1 Pro

Video

Kuaishou's older Kling V2.1 Pro image-to-video model supports a first frame plus an optional tail frame image. Current pricing is 50 credits for 5 seconds and 100 credits for 10 seconds.

Why pick it

Image-to-video only, with a narrower project

Best for
Before-and-after or start-and-end frame shot tests
Input
Text / Reference / Image
Output
Video
Credits
50-100 credits per generation
Supports a first frame and an optional tail frameFixed 5-second and 10-second price tiers

Kuaishou

Kling V2.1 Standard

Video

Kuaishou's older Kling V2.1 Standard image-to-video model. Current pricing is 25 credits for 5 seconds and 50 credits for 10 seconds.

Why pick it

Image-to-video only

Best for
Animating one product still into a quick motion test
Input
Text / Reference / Image
Output
Video
Credits
25-50 credits per generation
Fixed 5-second and 10-second price tiersSupports `negative_prompt` and `cfg_scale`

Kuaishou

Kling AI Avatar Pro

Video

Kuaishou's Kling AI Avatar Pro higher-quality talking-avatar model, using one portrait image plus one audio clip to generate lip-synced avatar video. Rivya currently prices it at a fixed 16 credits per generation.

Why pick it

Fixed portrait-plus-audio high-quality talking-avatar project

Best for
Higher-quality talking-avatar videos
Input
Text / Reference / Image / Audio
Output
Video
Credits
16 credits per generation
Fixed 16-credit pricing on RivyaBetter fit for quality-first lip-sync output

Kuaishou

Kling AI Avatar Standard

Video

Kuaishou's Kling AI Avatar Standard talking-avatar model, using one portrait image plus one audio clip to generate lip-synced avatar video. Rivya currently prices it at a fixed 8 credits per generation.

Why pick it

Fixed portrait-plus-audio talking-avatar project

Best for
Talking-avatar videos
Input
Text / Reference / Image / Audio
Output
Video
Credits
8 credits per generation
Fixed 8-credit pricing on RivyaStraightforward lip-sync path

MeiGen-AI

Infinitalk

Video

Infinitalk is a portrait-plus-audio talking-video model. Current pricing is metered by resolution and audio duration: 480p = 3 credits per second and 720p = 12 credits per second.

Why pick it

Fixed portrait-plus-audio talking-video project

Best for
Talking-avatar videos
Input
Text / Reference / Image / Audio
Output
Video
Credits
3 or 12 credits per second
Credits follow resolution and verified audio durationSupports 480p and 720p output tiers

Runway

Runway

Video

Runway is a standalone video model that supports both text-to-video and image-to-video. Public pricing evidence currently confirms only 6 generation tiers, so Rivya keeps it on the verified set: `720p_5 = 12`, `720p_10 = 30`, and `1080p_5 = 30`.

Why pick it

Clear public price evidence for both text and image tiers

Best for
5-second launch teasers and social ads
Input
Text / Reference / Image
Output
Video
Credits
12-30 credits per generation
Text and image generation share one aligned model entryText mode keeps `aspectRatio` while image mode follows the source image ratio

Runway

Runway Aleph

Video

Source-video transformation project for reworking an existing clip into a new visual result. Use Aleph when the motion comes from your input footage and the creative direction comes from your prompt, with a fixed 90-credit price.

Why pick it

Built around one source video, so the motion foundation comes from your footage rather than a blank generation

Best for
Reworking an approved source clip into a different art direction or mood
Input
Text / Reference / Video / Image
Output
Video
Credits
90 credits per generation
Prompt-led transformation with one optional reference image for style or subject guidanceKeeps Aleph separate from standard Runway 5- or 10-second text/image generation

Luma

Luma Modify Video

Video

Standalone source-video rewrite project for pushing one existing clip into a new visual direction. Use it when the prompt should transform the footage itself, not just sharpen the export.

Why pick it

Purpose-built for source-video rewriting, not simple enhancement

Best for
Turning one approved source clip into a different mood, style, or art direction
Input
Reference / Video
Output
Video
Credits
30 credits per generation
Best on short clips with one rewrite goal and one English-initial promptBetter fit than upscalers when the look, atmosphere, or art direction should change

xAI

Grok Imagine Video

Video

xAI's video model with Fun/Normal/Spicy creative modes and 5 aspect ratios. Unique style presets for different creative tones — from playful to cinematic to edgy.

Why pick it

Unique Fun / Normal / Spicy creative modes

Best for
Stylized teaser clips and social-first motion
Input
Text / Reference / Image
Output
Video
Credits
From 10 credits per generation
480p and 720p output tiers with per-second billing6 to 30 second clips

OpenAI

Sora 2 Pro

Video

Sora 2's premium tier with Standard/High quality modes, 10s/15s clips, and watermark removal. Enhanced detail, lighting, and motion fidelity for professional video production.

Why pick it

Standard and High quality tiers for production use

Best for
Premium product films and launch clips
Input
Text / Reference / Image
Output
Video
Credits
From 75 credits per generation
Enhanced detail, lighting, and motion fidelity10s or 15s clips with 10K-character prompt support

OpenAI

Sora 2

Video

OpenAI's video model for text-to-video and image-to-video with realistic world simulation, synced audio, 10s/15s clips, landscape/portrait outputs, and optional watermark removal.

Why pick it

Physically accurate world simulation

Best for
Short cinematic product or launch teasers
Input
Text / Reference / Image
Output
Video
Credits
From 6 credits per generation
10s or 15s clip duration with long prompt support (10K chars)Landscape and portrait orientation options

OpenAI

Sora Watermark Remover

Video

Sora's watermark-removal post-processing model on Rivya for finished public Sora share links. Use it after the video is already done when the remaining task is watermark removal plus choosing S3 or OSS delivery.

Why pick it

Built specifically for public `sora.chatgpt.com` share links, not generic uploaded videos

Best for
Removing the watermark from a public Sora share link before delivery
Input
Video
Output
Video
Credits
3 credits per run
Keeps watermark removal separate from Sora 2 and Sora 2 Pro generationOnly two decisions on Rivya: the public video URL and the output storage target

Topaz

Topaz Video Upscaler

Video

Topaz's delivery-grade video upscaler on Rivya for approved clips that only need more clarity at export. Use it when the shot, motion, and timing are already right and the remaining problem is resolution or final-file sharpness.

Why pick it

Best for already-approved clips where only clarity or delivery resolution is missing

Best for
Sharpening an approved clip before client delivery, presentation, or publishing
Input
Reference / Video
Output
Video
Credits
12 credits per run
Single-video, no-prompt project keeps it useful as a post-edit finishing stepSimple 1x, 2x, and 4x ladder with the current fixed 12-credit tier

Google

Veo3.1 Quality

Video

Google Veo 3.1's quality-first variant for premium text-to-video and image-led generation. Higher-fidelity visuals, stronger motion realism, and background audio by default make it Rivya's higher-end Veo option.

Why pick it

Higher-end Veo output path on Rivya

Best for
Hero launch films and premium brand spots
Input
Text / Reference / Image
Output
Video
Credits
From 150 credits per generation
Better fit for premium brand spots and hero scenesBackground audio is included by default

Google

Veo3.1 Fast

Video

Google Veo 3.1's fast variant with triple-mode support: text-to-video, image-to-video, and reference-to-video. Up to 3 reference images, native audio, and mode-aware aspect-ratio controls make it useful for quick cinematic clips.

Why pick it

Triple mode: text / image / reference-to-video

Best for
Fast ad concepts with native audio
Input
Text / Reference / Image
Output
Video
Credits
From 20 credits per generation
Up to 3 reference images for guided generationNative audio generation with video

Google

Veo3.1 Lite

Video

Google Veo 3.1's lowest-cost variant. Rivya currently exposes the smallest stable subset only: text-to-video and image-to-video at a fixed `10` credits per generation.

Why pick it

Fixed price of 10 credits for both text-to-video and image-to-video on Rivya

Best for
Low-cost Veo experiments before paying for higher tiers
Input
Text / Reference / Image
Output
Video
Credits
10 credits / generation
Keeps the Veo 3.1 base generation flow at the lowest current cost tierSupports both prompt-only and image-driven generation

Suno

Suno Music

Audio

Suno Music is Rivya's text-to-music model for turning one short brief into a first song draft with or without vocals. It keeps the fixed `12` credit entry point and exposes `Extend Music` as the next step after a successful track.

Why pick it

Documented fixed price of 12 credits per generation

Best for
Testing song direction before committing to a longer production flow
Input
Text
Output
Audio
Credits
12 credits / generation
First release stays narrow instead of exposing the full Suno family at onceSuccessful tracks can continue through an Extend Music action

Suno

Suno Sounds

Audio

Suno Sounds is Rivya's lightweight text-to-sound model for ambience loops, background sound, and short sonic sketches. It keeps the documented fixed price of `3` credits per generation and lets successful results continue into `Vocal Separation`.

Why pick it

Documented fixed price of 3 credits per generation

Best for
Generating ambience beds, loops, and environmental sound ideas
Input
Text
Output
Audio
Credits
3 credits / generation
First release only exposes loop, BPM, and Key as the lowest-risk parameter subsetKeeps the current Suno audio result chain with standard audio URLs

Suno

Suno Lyrics

Audio

Suno Lyrics is Rivya's lyric-generation model for turning one theme or mood into song words at a fixed cost of `1` credit per request.

Why pick it

Fixed 1-credit lyric generation

Best for
Drafting lyrics before generating a full song
Input
Text
Output
Audio
Credits
1 credit / generation
Only exposes the lowest-risk prompt-only parameter subsetKeeps the async task flow while allowing success without media URLs

ElevenLabs

ElevenLabs Dialogue V3

Audio

ElevenLabs' multi-speaker dialogue model on Rivya. It is built for role-based speech generation, with individual voice assignments, stability controls, and dialogue-ready pacing for podcasts, interviews, and character scenes.

Why pick it

Multi-speaker dialogue generation

Best for
Two-host podcast intros and debate segments
Input
Text
Output
Audio
Credits
Credits based on duration or length
Individual voice assignment per characterAdjustable stability for consistent delivery

ElevenLabs

ElevenLabs Turbo 2.5

Audio

ElevenLabs' fast text-to-speech model on Rivya. With low-latency voice generation and adjustable stability, similarity, style, and speed, it is built for rapid voiceover drafts and interactive TTS projects.

Why pick it

Fastest ElevenLabs TTS — optimized for low latency

Best for
Product demo and app walkthrough voice-overs
Input
Text
Output
Audio
Credits
Credits based on duration or length
Adjustable stability, similarity, style, and speedMultiple voice presets with context-aware generation

ElevenLabs

ElevenLabs Multilingual V2

Audio

ElevenLabs' multilingual text-to-speech model on Rivya, supporting about 30 languages with auto-detection. It is the stronger option for localization, cross-language delivery, and more natural multilingual voiceovers.

Why pick it

Auto-detects and generates ~30 languages

Best for
Localized product demos and onboarding videos
Input
Text
Output
Audio
Credits
Credits based on duration or length
Humanlike intonation and tonal nuanceSame voice controls: stability, similarity, style, speed

ElevenLabs

ElevenLabs Sound Effect V2

Audio

ElevenLabs' text-to-sound model on Rivya for short effects, transitions, and ambience loops. Generate 0.5–22 second audio clips with adjustable prompt influence, loop mode, and 19 output formats for editing, product, or game projects.

Why pick it

Configurable 0.5–22 second audio duration

Best for
UI clicks, notification sounds, and app feedback cues
Input
Text
Output
Audio
Credits
Credits based on duration or length
Adjustable prompt influence strengthLoop mode for seamless repeating audio

ElevenLabs

ElevenLabs Audio Isolation

Audio

ElevenLabs' audio cleanup and voice-isolation model on Rivya. Upload one recording to isolate vocals, remove background noise, and clean spoken audio before editing or publishing.

Why pick it

Upload-based audio isolation — no prompt needed

Best for
Cleaning interview or podcast recordings before editing
Input
Reference / Audio
Output
Audio
Credits
Credits based on duration or length
Vocal separation and background noise removalMetered billing by audio duration

Found a few worth trying?

Shortlist models here, then test them inside Rivya without switching apps, wallets, or project history.
6 signup credits
Quick signup