Text to Speech
Text-to-Speech endpoint. Routes by model (orpheus-3b-tts | spark-tts). Returns a signed audio URL (response_mode=‘url’). Replaces /tasks/modal/tts, /tasks/runpod/tts, and /tasks/modal/orpheus/tts.
Authorizations
The access token received from the authorization server in the OAuth 2.0 flow.
Body
Text-to-speech request.
Some fields apply only to specific model/platform combinations; the SpeechService validates combinations and returns 400 on a mismatch.
Text to synthesize.
1TTS model.
orpheus-3b-tts, spark-tts Voice/speaker. spark-tts: SpeakerID name (e.g. 'luganda_female') or id (e.g. '248'); orpheus-3b-tts: catalog tag (e.g. 'salt_lug_0001').
url (signed URL), stream (raw audio), or both (SSE). stream/both require model='spark-tts' on platform='modal'.
url, stream, both orpheus only (ISO 639-3).
orpheus only.
orpheus only.
runpod-spark only.
Response
Successful Response
Normalized response for response_mode='url' across all providers.
Signed URL to the generated audio.
Model used.
Resolved voice/speaker.

