Generate personal speech
POST
https://api.vidmoat.com/v1/speech/generationsBearer tokenScope
speech.generateConfigured credits per started 1,000 Unicode charactersTry it in the playgroundSubmit a script using an authorised ready personal voice. The complete script is chunked without dropping text. Returns a durable job ID; poll instead of resubmitting.
Body#
voiceIdstringrequiredYour ready voice ID.textstringrequired1 to 8,000 Unicode characters; output capped at ten minutes.languageenumdefaultenOnly tested, installed languages are accepted.One ofenspeednumberdefault1Pitch-preserving speaking pace, 0.75 to 1.25.expressionnumberOptional delivery intensity, 0 to 1. Supported only when capabilities.settings.expression exists. Subtle .25, balanced .5, animated .75; no guarantee of named emotions. Unsupported controls are rejected.projectIdstringOptional owned/member project receiving the audio. The generated output is authorised for that project; the voice reference stays private.
Response#
Returns 202.
Errors#
Besides the errors any request can get (authentication, rate limits):
| Status | Code | When |
|---|---|---|
| 409 | conflict | The idempotency key belongs to different inputs, or the job is not in the required state. |
| 503 | unavailable | Inference, private storage, configured pilot billing or the limiter is unavailable. Nothing new is charged before admission. |