Text to speech

POST

/v1/audio/speech

Converts input text into spoken audio. Returns raw audio bytes in the requested format.

Request body

Field	Type	Required	Notes
`model`	string	Yes	A TTS model id from your catalog (e.g. `myt/myt_tts`).
`input`	string	Yes	Text to synthesise.
`voice`	string	Yes	A voice id supported by the model. Available voices are model-specific — open the model's detail page in the catalog to see its voices.
`response_format`	string	No	Audio format (model-dependent), e.g. `mp3` (default), `opus`, `aac`, `flac`, `wav`, `pcm`.
`speed`	number	No	Playback speed multiplier, where the model supports it. Default `1.0`.

Example request

{
  "model": "myt/myt_tts",
  "input": "Welcome to myt AI Cloud. Your gateway to AI models.",
  "voice": "<voice-id>",
  "response_format": "mp3"
}

Response

The response body is raw audio bytes. The Content-Type header matches the requested format (e.g. audio/mpeg for mp3). Write the bytes directly to a file.

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>"}'

Errors

Status	When
`400`	Input too long, unsupported voice or format
`401`	API key missing or invalid
`429`	Rate limit or budget exceeded

Code examples

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>"}'

Full parameter reference: Audio speech.