Finalize streaming session
Collect all streamed audio into a complete WAV and return as base64.
Waits for generation to complete, concatenates all chunks, stores the result as the last generation result, and removes the session. Call this after the audio stream finishes to get the full audio.
session_id*Session IdSuccessful Response
application/json- response
success*SuccessWhether generation completed successfully
status*StatusHuman-readable status message
audio_base64?|Base64-encoded audio output (WAV format)
error_code?|Machine-readable failure code when success is false
error_detail?|Extra detail for the failure code
curl -X POST 'http://127.0.0.1:8100/api/v1/streaming/string/finalize'{ "success": true, "status": "Generated successfully", "audio_base64": "UklGRi4AAABXQVZFZm10IBAAAA...", "error_code": "language_unsupported", "error_detail": "string"}Stream session audio as WAV GET
Stream generated audio progressively while synthesis runs. Both formats are replayable and resumable: reads never consume the session buffer, and `Range: bytes=N-` requests resume from byte N (206), so players like ExoPlayer can recover from network drops. MP3 is encoded once per session into a buffer all readers share. The stream ends when generation completes. 10-minute hard timeout.
List saved voices GET
Return all saved voices, optionally filtered by type (clone or design).