Voice AI Beta — Sirius

Create Speech Task

Create a Text-to-Speech task with Sirius. Provide exactly one of voice (preset, from GET /v1/tts/sirius/voices), voice_asset_id (your voice clone) or voice_design_id (your saved voice design). Preset voices additionally accept free-text style instructions. Cost: ⌈characters / 2⌉ credits, refunded automatically on failure.

Example

curl -X POST https://genaipro.io/api/v1/tts/sirius \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "Xin chào, đây là GenAIPro", "voice": "arcturus", "style": "speak softly, warm tone"}'

Rate limit: 30 requests/minute

post/v1/tts/sirius

Request body

titlestring

Optional title (derived from content when empty)

contentstring required

Text to convert to speech

voicestring

Preset voice id (from GET /v1/tts/sirius/voices). Provide exactly one of voice / voice_asset_id / voice_design_id.

voice_asset_idstring

Voice clone id (from POST /v1/tts/voice-assets).

voice_design_idstring

Saved voice design id (from POST /v1/tts/sirius/voice-designs/{id}/save).

stylestring

Optional plain-text delivery instructions (e.g. speak softly, sad tone). Preset voices only — rejected with 400 when combined with a personal voice.

callback_urlstring

Optional webhook — receives the task object when the task completes or fails

Example request

{
  "content": "Xin chào, đây là GenAIPro",
  "voice": "arcturus"
}

Response

Task created — credits already deducted (cost)

idstring

Task ID (poll via the provider's GET /{id})

Voice AI Beta task lifecycle: pending → cloning (clone flow only) → queued → processing → merging → process_merging → completed | failed.

providerstring

total_lengthinteger

Billable characters (encoder units ≈ UTF-8 bytes)

costinteger

Credits deducted for this task

Example response

{
  "status": "completed",
  "provider": "lyra"
}

Changes

No recorded changes to this endpoint across all 1 revision of this API.