Passer à la navigation
ElevenAPIRealtime Translation

WebSocket

The Realtime Translation WebSocket API streams translation audio continuously to a target language given source audio. Currently for enterprise workspaces only.

Handshake

WSS
/v1/translation/realtime

En-têtes

xi-api-keystringOptionnel

Paramètres de requête

authorizationstringOptionnel
Your authorization bearer token.
target_languagestringRequis

Target language as an ISO 639 code (e.g. de, es, fr, zh).

source_languagestringOptionnel

Source language as an ISO 639 code. When omitted the server auto-detects the spoken language.

voice_idstringRequis
Voice ID used for the translated speech output.
input_formatanyOptionnel
Audio encoding format for realtime translation input.
output_formatanyOptionnel
Audio encoding format for realtime translation output.
tts_model_idenumOptionnelPar défaut eleven_v4_turbo
TTS model used to synthesize the translated speech.
Valeurs autorisées:
apply_text_normalizationenumOptionnelPar défaut off

This parameter controls text normalization with three modes: ‘auto’, ‘on’, and ‘off’. When set to ‘auto’, the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With ‘on’, text normalization will always be applied, while with ‘off’, it will be skipped.

Valeurs autorisées:
eagernessenumOptionnelPar défaut medium
How eagerly translation starts while the speaker is still talking. 'high' starts translating soonest for the lowest latency. 'low' waits for more of the sentence, giving higher quality translations with more delay.
Valeurs autorisées:
client_session_idstringOptionnel

Optional client-defined session identifier for tracking purposes.

enable_zrmbooleanOptionnelPar défaut false

When enable_zrm is set to true, zero retention mode will be used for the request. Sensitive content (transcripts, translations, and TTS text) is not written to application logs or session history. Zero retention mode may only be used by enterprise customers.

Envoyer

inputAudioChunkobjectRequis
Send a chunk of audio for translation.
OR
endOfStreamobjectRequis
Signal that the audio stream has ended.

Recevoir

sessionStartedobjectRequis
Sent by the server when the session is initialized.
OR
statusobjectRequis
Session lifecycle update indicating the session has started or stopped.
OR
partialTranscriptobjectRequis
Interim transcription of the source audio.
OR
finalTranscriptobjectRequis
Final transcription of a segment of source audio.
OR
translationobjectRequis
Translated text in the target language.
OR
audioobjectRequis

Base64-encoded audio of the translated speech.

OR
errorobjectRequis
Error encountered during translation.
OR
Translate Auth ErrorobjectRequis
Authentication failed for the session.
OR
Translate Rate Limited ErrorobjectRequis
The request rate limit was reached.
OR
Translate Queue Overflow ErrorobjectRequis
Audio was sent too frequently and the session was terminated.
OR
Translate Input ErrorobjectRequis

An input message could not be handled; check the message format.

OR
Translate Transcriber ErrorobjectRequis
The transcriber failed to process the audio.
OR
Translate Translation ErrorobjectRequis

Translation failed for a segment; the session continues.

OR
Translate Audio Output ErrorobjectRequis

Audio output for a segment failed or was dropped; the session continues.

OR
Translate Quota Exceeded ErrorobjectRequis

The workspace is out of credits; the session is closed.

OR
Translate Payment Issue ErrorobjectRequis

The workspace has a payment issue or is suspended; the session is closed.

OR
Translate Unaccepted Terms ErrorobjectRequis

The workspace has not accepted terms required for this feature; the session is closed.