Speech Streaming API

Use stream_format=sse to receive audio events, or audio to receive a binary stream.

POST /v1/audio/speech

Set KITSCH_OPENAI_BASE_URL to your Audio API URL ending in /v1.

curl "$KITSCH_OPENAI_BASE_URL/audio/speech" \
  -H "Authorization: Bearer $KITSCH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kitsch-voice","voice":"<voice_id>","input":"Hello.","response_format":"wav","stream_format":"sse"}'

Response

Content-Type: text/event-stream.

event: speech.audio.delta
data: {"type":"speech.audio.delta","audio":"<BASE64_AUDIO>"}

event: speech.audio.done
data: {"type":"speech.audio.done"}

Decode each speech.audio.delta event's base64 audio in order and concatenate the bytes. speech.audio.done marks the end of the transfer.

Response​

Response