The WebSocket API delivers low-latency text-to-speech streaming. Use it when you need immediate playback, conversational agents, or continuous audio synthesis.
Key Features
- Real-time audio – Receive PCM or MP3 chunks as they are generated.
- Flexible payloads – Choose JSON frames (base64) or raw binary streams.
- Connection-aware errors – Separate recoverable synthesis errors from unrecoverable connection failures.
Before you stream:
- Confirm your account has Business-plan WebSocket access.
- Retrieve your API token (
Authorization: Bearer ...).
- Select an eligible
voice_uuid.
Continue with Receiving Audio for request parameters and response shapes.
