Audio speech

POST

/v1/audio/speech

Synthesises speech from input text. Returns binary audio.

Request (JSON)

Field	Type	Notes
`model`	string	A TTS model id from your catalog, e.g. `myt/myt_tts`.
`input`	string	Text to synthesise.
`voice`	string	A voice id supported by the model (model-specific — see the model detail page).
`response_format`	string	Optional, model-dependent: `mp3`, `opus`, `aac`, `flac`, `wav`, `pcm`.
`speed`	number	Optional, where supported.

Response

Raw audio bytes with Content-Type matching the requested format.

Errors

400 for validation issues; 401 unauthorised; 429 rate limited.

Example

curl -sS --request "POST" \
  --url "$MYT_BASE_URL/audio/speech" \
  --header "Authorization: Bearer $MYT_API_KEY" \
  --header "Content-Type: application/json" \
  --output "speech.mp3" \
  --data '{"model":"myt/myt_tts","input":"Hello from myt AI Cloud.","voice":"<voice-id>"}'