Saltar a la navegación
ElevenAPIRealtime Translation

WebSocket

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

Protocolo de enlace

WSS
/v1/translation/realtime

Encabezados

xi-api-keystringOpcional

Parámetros de consulta

authorizationstringOpcional
Your authorization bearer token.
target_languagestringRequerido

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

source_languagestringOpcional

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

voice_idstringRequerido
Voice ID used for the translated speech output.
input_formatanyOpcional
Audio encoding format for realtime translation input.
output_formatanyOpcional
Audio encoding format for realtime translation output.
tts_model_idenumOpcionalValor predeterminado: eleven_v4_turbo
TTS model used to synthesize the translated speech.
Valores permitidos:
apply_text_normalizationenumOpcionalValor predeterminado: 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.

Valores permitidos:
eagernessenumOpcionalValor predeterminado: 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.
Valores permitidos:
client_session_idstringOpcional

Optional client-defined session identifier for tracking purposes.

enable_zrmbooleanOpcionalValor predeterminado: 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.

Enviar

inputAudioChunkobjectRequerido
Send a chunk of audio for translation.
OR
endOfStreamobjectRequerido
Signal that the audio stream has ended.

Recibir

sessionStartedobjectRequerido
Sent by the server when the session is initialized.
OR
statusobjectRequerido
Session lifecycle update indicating the session has started or stopped.
OR
partialTranscriptobjectRequerido
Interim transcription of the source audio.
OR
finalTranscriptobjectRequerido
Final transcription of a segment of source audio.
OR
translationobjectRequerido
Translated text in the target language.
OR
audioobjectRequerido

Base64-encoded audio of the translated speech.

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

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

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

Translation failed for a segment; the session continues.

OR
Translate Audio Output ErrorobjectRequerido

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

OR
Translate Quota Exceeded ErrorobjectRequerido

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

OR
Translate Payment Issue ErrorobjectRequerido

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

OR
Translate Unaccepted Terms ErrorobjectRequerido

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