Sign up freeSign in
allmodels.ioDocs
Realtime WebSocket referenceElevenLabs SDK-compatible realtime STT

Realtime STT client frames

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.

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

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.

ElevenLabs SDK-compatible realtime STT

Address

/el/v1/speech-to-text/realtime

Description

ElevenLabs realtime STT protocol across supported STT providers.

Authorization

xi-api-key<token>

AllModels API key (ElevenLabs SDK convention).

In: header

Messages

Stream-input TTS server frames SEND

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

Realtime STT server frames SEND

Reference for the ElevenLabs-compatible events AllModels returns on realtime STT: session start, partial and committed transcripts, and errors.