Realtime event reference

Review the API reference for the Realtime Speech to Text API for more information on the API and its options.

committed_transcript is the stable, final event for each segment. The public API does not emit a separate final_transcript event.

Sent events

Event	Description	When to use
`input_audio_chunk`	Send audio data for transcription	Continuously while streaming audio

Event	Description	When received
`session_started`	Confirms connection and returns session configuration	Immediately after WebSocket connection is established
`partial_transcript`	Live transcript update for the in-progress segment. Later partials replace earlier ones	During audio processing, before a commit is made
`committed_transcript`	Settled transcript for a segment. This is the stable, final text for the segment and will not change	After a commit (either manual or VAD triggered)
`committed_transcript_with_timestamps`	Committed transcript with word-level timestamps and the detected `language_code`	Sent after the committed transcript. Only received when `include_timestamps=true` or `include_language_detection=true` is included in the query parameters
`committed_transcript_entities`	Entities detected in the committed transcript segment, with character offsets	Sent shortly after each committed transcript. Only received when `entity_detection` is included in the query parameters
`edited_transcript`	Edited version of the committed transcript segment, alongside the original committed text	Sent shortly after each committed transcript. Only received when `transcript_edit` is included in the query parameters

If an error occurs, an error message will be returned before the WebSocket connection is closed.

Error Type	Description
`auth_error`	An error occurred while authenticating the request. Double check your API key
`quota_exceeded`	You have exceeded your usage quota
`transcriber_error`	An error occurred while transcribing the audio.
`input_error`	An error occurred while processing the audio chunk. Likely due to invalid input format or parameters
`invalid_request`	The connection parameters were rejected. Check the query parameters against the API reference
`error`	A generic server error
`commit_throttled`	The commit was throttled due to too many commit requests made in a short period of time
`unaccepted_terms`	You haven't accepted the terms of service to use Scribe. Please review and accept the terms & conditions in the ElevenLabs dashboard
`rate_limited`	You are rate limited. Please reduce the amount of requests made in a short period of time
`queue_overflow`	The processing queue is full. Please send fewer requests made in a short period of time
`resource_exhausted`	Server resources are at capacity. Please try again later
`session_time_limit_exceeded`	Maximum session time has been reached. Please start a new session or upgrade your subscription
`chunk_size_exceeded`	The audio chunk size is too large. Please reduce the chunk size
`insufficient_audio_activity`	You haven't sent enough audio activity to maintain the connection