audio

Generate Speech

post/v1/audio/speech

Request

  • Base URL: https://api.corent.tech (the document declares no server; this is the origin it was published from)
  • URL: https://api.corent.tech/v1/audio/speech
  • Auth: HTTP bearer

Headers

Idempotency-Keystring nullable

Request body

textstring required
voice_idstring nullable
modelstring nullable

Direct model access: pin an exact speech model by name, e.g. "corent-eleven-multilingual-v2". GET /v1/models publishes every name in that corent- spelling; older spellings of the same model (the bare name, historical route names) are still accepted here, so existing integrations keep working.

stabilitynumber nullable

0 to 1. Low is more expressive and more variable take to take; high is steadier.

similaritynumber nullable

0 to 1. How closely to hold the original voice's character.

stylenumber nullable

0 to 1. Extra expressiveness. Costs a little latency.

speednumber nullable

Playback speed multiplier; 1.0 is natural pace.

languagestring nullable

ISO language code for the multilingual models, e.g. "en" or "pt-BR".

output_formatstring nullable

Delivered audio format, e.g. "mp3", "wav", or an exact "mp3_44100_128".

customer_idstring nullable

Optional tag for YOUR end user, so you can attribute spend: 1 to 128 characters from A-Z a-z 0-9 . _ : @ -. Stored on the job, returned on receipts, and filterable with GET /v1/account/usage?customer_id=...

Response

Successful Response

idstring required
statusstring required
audio_urlstring required

Changes

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