Skip to content

Generate personal speech

POSThttps://api.vidmoat.com/v1/speech/generations
Bearer tokenScope speech.generateConfigured credits per started 1,000 Unicode charactersTry it in the playground

Submit 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#

  • voiceIdstringrequired
    Your ready voice ID.
  • textstringrequired
    1 to 8,000 Unicode characters; output capped at ten minutes.
  • languageenumdefault en
    Only tested, installed languages are accepted.
    One of en
  • speednumberdefault 1
    Pitch-preserving speaking pace, 0.75 to 1.25.
  • expressionnumber
    Optional 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.
  • projectIdstring
    Optional 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):

StatusCodeWhen
409conflictThe idempotency key belongs to different inputs, or the job is not in the required state.
503unavailableInference, private storage, configured pilot billing or the limiter is unavailable. Nothing new is charged before admission.