Synthesize speech for one input via Orpheus-3B
Legacy Text to Speech
Synthesize Speech (Orpheus-3B)
deprecated
Calls the Orpheus-3B Modal vLLM inference app, uploads the generated WAV to Google Cloud Storage, and returns a v4 presigned download URL valid for the configured expiry window (default 30 minutes), together with metadata and stage-by-stage latency timings.
POST
Synthesize speech for one input via Orpheus-3B
Authorizations
The access token received from the authorization server in the OAuth 2.0 flow.
Body
application/json
Text to synthesize.
Required string length:
1 - 2000Speaker tag from the Orpheus finetune set (see GET /speakers).
Optional ISO 639-3 language code (e.g. 'lug', 'eng'). If set, speaker_id must belong to it.
RNG seed for reproducibility.
Required range:
0 <= x <= 2Required range:
x <= 1Required range:
1 <= x <= 2Required range:
64 <= x <= 4096Response
Successful Response
Required string length:
1 - 2083
