↓
Rivya AI Docs

Choose a Rivya AI model for your task

Use Rivya's catalog to check input support and settings, compare credits for the same output, and review one result before planning more tasks.

Last reviewed on November 11, 2026

Start with the result you need and the material you already have. Then use the AI Models catalog to find a model that accepts those inputs and can perform that operation today. A catalog listing is not a promise of access, quality or API support.

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.

Match the operation before comparing models

Define the job in one sentence, including the starting material and the result you want. For example: “Animate this approved product image.” That gives you an image input to match with a video model.

What you needWhere to startWhat to verify
A draft, explanation or conversationChatWhich text or image inputs the model accepts and the context needed for the reply. Check facts and calculations yourself.
A new image from a written descriptionImageText-to-image support and the required output dimensions.
An edit to an existing imageImage models with reference inputSupport for the specific edit, file requirements and which details must remain unchanged.
A moving scene from text or an imageVideoText-to-video or image-to-video as appropriate, plus supported duration and framing.
Narration, music, lyrics or a new soundAudioThe model's speech, sound or text output, supported voices or languages, and required inputs. Suno Music supports new custom-mode generation. Music extension, WAV conversion and vocal separation from Music results remain unavailable.

Video-to-video, motion control and cleanup of an uploaded recording need different kinds of models, even though their outputs may share a format. ElevenLabs Sound Effect V2 and Audio Isolation are paused. Suno Sounds generates new audio from a description; its vocal separation action is limited to eligible Sounds results. It cannot clean or isolate an uploaded recording. Suno Music supports new custom-mode generation. Music extension, WAV conversion and vocal separation from Music results remain unavailable.

For calculations or a problem you want to work through, start with AI Calculator and AI Solver. These tools supply task instructions to a configured chat model. Check the reasoning and answers before using them.

Narrow the catalog with search and filters

Use the catalog in this order:

  1. Choose the output category: chat, image, video or audio.

  2. Choose an input filter if needed: text, image, video, audio or reference material.

  3. Search for a model name or a short phrase describing the task. The search checks catalog text; it does not run your request.

  4. Open a candidate's detail page to check its current status, supported modes and input requirements.

The count shows matching entries, including models that are paused or not yet available. An input label narrows the list; check each candidate's actual mode and file requirements. Credit hints help you compare options, but the catalog does not rank models by the lowest total cost or measured runtime.

If nothing matches, clear the search and filters and try a broader term. Clearing just the search text keeps the category and input filters; the results area's reset control clears all three. You can copy the current page address to preserve the search and filter selection, but the matching entries can change later.

Check the model page and input requirements

Check Model Availability before preparing a run. A paused or coming-soon model cannot accept a new request just because its page remains public; buying credits does not unlock it.

For a model you can currently run, read its description, modes, input summary, prompt requirements and any FAQ. Open the Studio form and check:

  • Whether your operation needs a prompt, a file, a URL or several inputs together.

  • File types, count, size, duration or dimension limits, and whether each upload has finished.

  • Available parameters and allowed combinations for the chosen mode.

  • The intended role of each reference: subject, composition, style, motion or audio source.

Use Model Fields and Parameters, References and Uploads and Image References for those checks. A reference can guide a result but does not guarantee exact logos, lettering, geometry or product identity. Inspect important details against the original before delivery.

Compare costs using the same intended result

A chat reply, a short video draft and a longer clip are different jobs. Set the required output and essential settings first, then compare the estimates offered by models that can meet them. Keep duration and resolution comparable for video; comparing different deliverables will not show which model costs less for your task.

Media estimates can depend on the model, settings, input duration or text. Chat charges can depend on tokens and the conversation included in the request. Start with the catalog's credit hint, then check the form's estimate and Credits & Billing for reserved credits and the final charge.

Choose quality, duration and aspect ratio for the intended placement. A lower setting is useful only if it still tests what matters. More credits, higher resolution or a longer clip do not by themselves fix a wrong instruction or guarantee a better result.

Review one focused attempt before expanding

Decide what a useful result must get right and test a small version of the real task. For an approved bottle photo you want to animate, check whether a compatible image-to-video model preserves the bottle’s shape, keeps the label readable and adds the movement you asked for. Use this as an evaluation example; it is not a measured result or ranking.

Keep your prompt, original files and selected settings with the result. Check the condition you chose. If it fails that check, review the input, instructions, settings and possible model limits, then change one relevant factor for the next attempt. Each new submission can cost credits. Wait for the outcome of an unclear earlier request before submitting the same work again.

Switching models can reset settings and remove references the new model cannot use. Review the whole form after the switch. Save useful files through Output Downloads and keep your own prompt, source files and settings; History holds task records, not a complete editing project. How to Pick the Right Model gives more examples of choosing by task.

Find the documentation for a specific model

Start with the candidate's catalog detail page for its description and current access. Read the mode, input, parameter and FAQ details shown for that exact model. Models in the same family can offer different operations and controls.

For API use, read API Models and API Model Reference before settling on a model. If it has a /docs/api/models/{id} reference, check api_status, supports_direct_generation and api_input_status alongside the documented fields and input notices. Check whether your reference mode requires the Files API; a text-only example does not prove reference support.

The API list supplies the model ID to use. Check Studio access and API input support separately. If no available model accepts your inputs and performs the required operation, Rivya may have no direct replacement for that task; another model name does not remove the mismatch.