Vai alla navigazione
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

Header

xi-api-keystringOpzionale

Parametri di query

authorizationstringOpzionale
Your authorization bearer token.
target_languagestringObbligatorio

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

source_languagestringOpzionale

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

voice_idstringObbligatorio
Voice ID used for the translated speech output.
input_formatanyOpzionale
Audio encoding format for realtime translation input.
output_formatanyOpzionale
Audio encoding format for realtime translation output.
tts_model_idenumOpzionalePredefinito a eleven_v4_turbo
TTS model used to synthesize the translated speech.
Valori consentiti:
apply_text_normalizationenumOpzionalePredefinito a 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.

Valori consentiti:
eagernessenumOpzionalePredefinito a 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.
Valori consentiti:
client_session_idstringOpzionale

Optional client-defined session identifier for tracking purposes.

enable_zrmbooleanOpzionalePredefinito a 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.

Invia

inputAudioChunkobjectObbligatorio
Send a chunk of audio for translation.
OR
endOfStreamobjectObbligatorio
Signal that the audio stream has ended.

Ricevi

sessionStartedobjectObbligatorio
Sent by the server when the session is initialized.
OR
statusobjectObbligatorio
Session lifecycle update indicating the session has started or stopped.
OR
partialTranscriptobjectObbligatorio
Interim transcription of the source audio.
OR
finalTranscriptobjectObbligatorio
Final transcription of a segment of source audio.
OR
translationobjectObbligatorio
Translated text in the target language.
OR
audioobjectObbligatorio

Base64-encoded audio of the translated speech.

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

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

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

Translation failed for a segment; the session continues.

OR
Translate Audio Output ErrorobjectObbligatorio

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

OR
Translate Quota Exceeded ErrorobjectObbligatorio

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

OR
Translate Payment Issue ErrorobjectObbligatorio

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

OR
Translate Unaccepted Terms ErrorobjectObbligatorio

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