POST /v1/text-to-speech/{voice_id} for non-streaming output and POST /v1/text-to-speech/{voice_id}/stream for streaming output.
Use the streaming endpoint for lower time-to-first-byte and chunked audio. Streaming supports mp3 and pcm output formats.
Timing metadata and realtime text input over WebSocket are planned.
Build with streaming
Stream text to speech
Inspect the streaming endpoint, SDK examples, request fields, and binary response.
Text to speech guide
Compare sync, async, and streaming delivery for real product workflows.
Output formats
Choose between
mp3 and pcm for streaming playback and audio pipelines.Rate limits
Handle concurrent generation limits and retryable streaming failures.