Sign up freeSign in
allmodels.ioDocs
Realtime WebSocket referenceElevenLabs SDK-compatible streaming-input TTS

Stream-input TTS server frames

Reference for the frames AllModels returns on the ElevenLabs-compatible stream-input TTS WebSocket: base64 audio chunks, completion, and errors.

The raw document is available at /audio/docs/asyncapi.yaml and from the API at api.allmodels.io/asyncapi.yaml.

Reference for the frames AllModels returns on the ElevenLabs-compatible stream-input TTS WebSocket: base64 audio chunks, completion, and errors.

ElevenLabs SDK-compatible streaming-input TTS

Address

/el/v1/text-to-speech/{voice_id}/stream-input

Description

ElevenLabs stream-input protocol across supported TTS providers.

Authorization

xi-api-key<token>

AllModels API key (ElevenLabs SDK convention).

In: header

Parameters

voice_id?string

Provider voice id (path segment), e.g. eve for Grok TTS. Forwarded to the routed provider verbatim — the router applies no default voice and recognises no placeholder; see defaults.tts.voice on GET /v1/providers for a recommended value per provider.

Messages

Stream-input TTS client frames RECEIVE

Reference for the ElevenLabs stream-input frames a client sends to stream text into TTS on AllModels: init, text chunks, flush, and close.

Realtime STT client frames RECEIVE

Reference for the audio chunk frames a client sends on the ElevenLabs-compatible realtime speech-to-text WebSocket at /el/v1/speech-to-text/realtime.