audivra docs
Start free

Or jump from this list on a smaller screen.

This is a page from the Audivra documentation. Developer exports — index: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.

Voice design

Create a custom voice from a natural-language description.

Describe gender, age, accent, and tone. Audivra seeds a speaker from the prompt, applies style DSP, then trains a clone embedding (neural restyle when GPU weights are installed).

Describe, preview, save

  1. Write a natural-language prompt — gender, age, accent, tone, use case.
  2. Preview audio without saving via POST /api/voices/design/preview.
  3. Audivra seeds a speaker from the prompt, applies style DSP, then trains a clone embedding (neural restyle when GPU weights are installed).
  4. Save the design — poll until status is ready, then use the UUID as voice_id.

Prompt tips

  • Be specific: "Warm Kenyan English female narrator, calm and authoritative" beats "nice voice".
  • Set language, gender, and age explicitly — they steer reference generation.
  • Optional preview_text controls the phrase synthesized for the speaker reference.

Dashboard & API

Voice design shares custom voice slots with cloning on paid plans. See Credits.