↓
Rivya AI Docs

Rivya features: AI chat, images, video, audio and tools

Find the right Rivya starting point for AI chat, images, video, audio, tools, and API access, with sign-in, credit, and availability limits explained.

Last reviewed on November 11, 2026

Rivya brings AI chat, image, video, and audio tasks into one account with a shared credit balance. Use it to write a brief, create a visual, generate a clip, or prepare a voice track. Choose the model for each task; combining the outputs into a finished project may still require your own editing tools.

Suno Speech: scenes and supplied scripts

Suno Speech — Suno Speech creates spoken audio with tone, rhythm and emotion. Simple mode writes a script from your scene; Advanced mode reads the script you provide.

Choose Simple to describe an announcement, introduction or spoken scene and let the model write it. Choose Advanced when the wording matters: your main text becomes the script, with optional delivery settings. Switching to Simple drops the Advanced settings.

Suno Speech generates expressive spoken audio and can add background music. For a script with one of the named Zephyr, Puck or Kore voices and WAV output, choose an available Gemini TTS model instead.

Gemini 3.8 Flash TTS · Gemini 3.8 Flash Lite TTS · Gemini 3.1 Flash TTS · Gemini 2.5 Pro TTS

New operation-specific paths

The catalog now separates Seedream 5.5 text generation, reference editing and layer decomposition. Video work can use Gemini Omni 1.2 Flash, while existing files have separate image and video upscale operations. Gemini 4 Carbon is a text-only chat path with an expiring quote.

MiniMax H3 Image, Claude Fable 5.2 and the existing Wan Animate 2 are Coming Soon announcements. They cannot create tasks, reserve credits or reuse examples for generation. Check current availability rather than treating every catalog entry as callable.

Choose a Starting Point

You want to…Start hereCheck before submitting
Draft, explain, or discuss somethingChatThe selected model and any attachment limits
Generate or edit an imageImageWhether the model supports your specific operation and references
Generate a videoVideoRequired text or references, supported duration, and output settings
Create speech, dialogue, short sounds, or lyricsAudioThe exact audio task and the model's current availability

The model catalog helps you narrow the choice. A listed model is not necessarily runnable, and an image-input label does not mean it supports every image-editing operation.

Browse First, Sign In to Run

You can browse public pages, compare models, and read examples without an account. Where a quick-start form is available, you can prepare your request there. Submitting a chat message or generation requires sign-in; supported public forms can run on the same page after sign-in. You do not have to move every request to Studio.

Studio provides the signed-in workspace for choosing models and working with your account's tasks. Check your draft, selected model, inputs, and estimated credits before sending, including after sign-in. Opening a page or filling in a prompt does not run the task. See public and signed-in workflows for the detailed steps.

Tools and Audio: Check the Specific Task

The live tools are AI Calculator and AI Solver. Both use Claude Sonnet 5 with task-specific instructions. Their tool forms use a fixed model and do not offer the ordinary Chat model picker. They help show calculations or reasoning, but their answers still need checking; they are not guaranteed-exact calculation engines. Other tool categories marked coming soon cannot yet be used.

Audio includes speech and dialogue. Suno Sounds and Suno Lyrics remain available for short sounds and lyric text. Suno Music supports new custom-mode generation. Music extension, WAV conversion and vocal separation from Music results remain unavailable. Existing Music records remain in History, and their results can be viewed and downloaded while the files remain accessible. Lyrics do not produce audio, and Sounds does not clean an existing recording. ElevenLabs Sound Effect V2 and Audio Isolation are also paused. The music workflow guide explains the current limits.

Start with a Prompt or Connect Your Own App

For software integration, start with the developer page. API execution requires a valid key with the appropriate permissions and an available API model. Being usable in Studio does not establish API support: check the model's API availability and input requirements.

The optional Rivya Prompt Clipper assembles a local brief from selected webpage text, or the page description when no text is selected, together with the page title and URL. Copy prompt copies the editable brief. The opening button opens the chosen Rivya category with attribution parameters; it does not pass the brief or source-page content to the form. Review and paste the text yourself, then check the model and required inputs before sending. Clipper does not run a model or spend credits, and it is not required to use Rivya.

Understand Cost and Save Your Work

Review plans and credit packs before buying. The account balance is shared across supported tasks; neither a public tool page nor a subscription means unlimited generation. The starting estimate shown for chat and tools can be lower than the credits reserved for a request. That reservation can account for conversation context, tool instructions, and an allowance for the reply. Estimates are not fixed final charges. Actual usage depends on the model and request. The credit guide explains estimates, reservations, settlement, and expiry.

Use History for saved tasks and conversations, and browse earlier records across its pages. It is not a permanent backup of every output or unsent draft, and some files expire. Download important files and keep your prompts and settings. Moving between chat, image, video, and audio does not automatically assemble a finished video or transfer an entire project.

Confirm Availability Before You Commit

Check the current model or tool page before uploading files, buying credits for a specific feature, or promising a delivery. Paused and coming-soon entries cannot be unlocked by paying. Availability can change, and an older blog example is not proof that its model is runnable today.

The availability guide explains the status labels. An available model still has input and parameter limits, and its status does not guarantee response time, uninterrupted service, or output quality.