AI Audio Workflows in Rivya: From Script to Delivery
Music creation and follow-ups are paused. Use Sounds or Lyrics, and view, check or download existing Music results.
Last reviewed on October 7, 2026
Speech and dialogue generation remain available in Audio Studio. Suno Music generation is currently paused, along with Music extension, WAV conversion and vocal separation from Music results. Suno Sounds and Suno Lyrics remain available. Existing Music tasks and results can still be viewed, checked for status and downloaded; Lyrics does not start a Music task.
For the actual fields, submission steps and result controls, use the Audio Studio guide. For a first-task walkthrough, read starting an AI audio workflow.
Start with the material you already have
| Starting material | What you want | Route |
|---|---|---|
| A finished script | One person reading it | ElevenLabs Turbo 2.5 or ElevenLabs Multilingual V2; check the model's supported languages and voices |
| A script with speaker turns | A spoken conversation | ElevenLabs Dialogue V3; assign text and a voice to every turn |
| A description of music | A song or instrumental draft | Suno Music — Paused |
| A description of a sound | Ambience, a loop or a short sound sketch | Suno Sounds |
| A topic for a song | Lyrics to review before making music | Suno Lyrics; the result is text |
| An existing recording | Cleaner speech with the original performance preserved | No currently available direct cleanup route; Audio Isolation is paused |
ElevenLabs Audio Isolation and Sound Effect V2 are currently unavailable. A catalog page is not proof of availability; check model status. Suno Sounds generates new sounds and cannot repair an uploaded recording or replace every dedicated sound effect.
Finish spoken words before choosing delivery settings
For narration, write the words the listener should hear. Keep creative instructions separate from that text: a request such as “make a calm introduction” may itself be read aloud. For dialogue, split the script into turns and choose a voice for each one.
For another language, preserve the meaning while adapting wording, sentence length and idioms for listening. Check names, numbers and abbreviations aloud. Changing the website language does not translate your script, and the model's supported languages may differ from Rivya's interface languages. The narration guide covers spoken explanations; the dubbing guide covers replacing dialogue in another language.
Keep lyrics, music and sound generation separate
Suno Music generation is currently paused, along with Music extension, WAV conversion and vocal separation from Music results. Music descriptions and instrumental settings here belong to the historical workflow, pending restoration. This illustrative brief is not a tested output; a description does not guarantee exact lyrics, duration or arrangement. This is historical reference only; if Music returns, use the model page and actual form available at that time. Suno Sounds — A sound description and any relevant loop, tempo or key settings Suno Lyrics — A lyric brief; the result is text, not a sung track
Vocal separation remains available only for eligible successful Suno Sounds results with the required track information. It is a separately charged new task, not an upload tool for arbitrary recordings; Music-source separation is paused. music workflows
Example: prepare narration and music for a product video
This is an example production sequence, not a tested output or an automatic Rivya pipeline:
Finish the scene order and spoken script. Decide which moments need speech, music or silence; keep pronunciation notes separately.
Generate a spoken draft from the script. Listen against the actual scenes and adjust wording or available speed settings where needed. Asking for a duration in the script does not enforce exact timing.
Use a downloaded existing Music result or create an available Sounds result. Listen to the ending and check loop joins; do not start a new Music task.
Download the accepted files, align and mix them in your editor, then review the complete video. Rivya does not automatically combine these separately generated tracks or synchronize translated speech with the original video.
Already have a recording to drive a speaking character or lip-sync a video? Start with audio uploads: those models need specific companion images or videos and produce video. They are different from generating narration. See voiceover for videos for the editorial workflow.
Budget for the whole sequence
Speech and dialogue estimates depend on text length. Sounds and Lyrics have their own task prices, and eligible Sounds vocal separation is charged separately. Music generation and its follow-ups are paused. Check the current estimate before submitting. credit rules Do not apply a paused model's duration-based pricing to a different active model.
Use a representative short draft to check a voice before committing to a longer script. A draft still costs credits, and it does not guarantee identical delivery in a later result. If a submission response is unclear, check the original task in History before submitting again. Follow failed-task and credit-return guidance for a recorded failure; disliking an otherwise completed result is a different case.
Keep the files needed for the next stage
Save the accepted audio, final script, language version and any pronunciation or editing notes together. Preserve original recordings separately. Before delivery, listen for missing words, wrong names, unexpected vocals and timing problems; confirm you can use the source material and result for the intended purpose. A paid plan does not grant rights to someone else's voice or protected work.
Download useful results promptly using output downloads. History is not a complete editing project or a promise of permanent file storage. When moving between a model page and Studio, keep an external copy of unsent text and settings; see public pages and signed-in workflows.