Multilingual Transcription

Transcribe live audio in any supported language, or several at once, with native code switching. Universal-3.5 Pro Streaming is multilingual by default. It follows speakers as they shift mid-sentence between languages like English and Spanish, French, Hindi or Mandarin, preserving exactly what was said without translating everything into a single language. No configuration is required. Hear what code switching sounds like, and how it’s transcribed.

English <> French

I said something like, j'ai dit à mes étudiants que it's time to really pay attention to what the idea of code-switching is.

English <> Hindi

मेरा रुकने का तो बहुत मन है, but I have an exam to give tomorrow.

English <> Mandarin

But this sentence, 我父母不工作了, you can see the 了 at the end of the sentence indicates that the situation now, my parents don't work, is different from what it was before.

Quickstart

Code switching is on by default. Open a streaming session with no language parameters and the model code-switches natively across all supported languages.

Python
Python SDK
Javascript
JavaScript SDK

CONNECTION_PARAMS = {
    "sample_rate": 16000,
    "speech_model": "universal-3-5-pro",
}

client.connect(
    StreamingParameters(
        sample_rate=16000,
        speech_model="universal-3-5-pro",
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-5-pro",
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-5-pro",
});

Steering toward known languages

When you know which languages a session will use, pass the language_codes connection parameter to steer the model toward them and improve language accuracy.

For a known subset, pass the codes you expect (for example, ["en", "es"]). The model still code-switches, but heavily biased to the languages you list.
For a monolingual session, pass a single-element list (for example, ["es"]).
For full multilingual, omit language_codes to keep native code switching across all supported languages.

Set the language_codes connection parameter when you open the WebSocket.

Python
Python SDK
Javascript
JavaScript SDK

CONNECTION_PARAMS = {
    "sample_rate": 16000,
    "speech_model": "universal-3-5-pro",
    "language_codes": ["en", "es"],
}

client.connect(
    StreamingParameters(
        sample_rate=16000,
        speech_model="universal-3-5-pro",
        language_codes=["en", "es"],
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-5-pro",
  language_codes: ["en", "es"],
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-5-pro",
  languageCodes: ["en", "es"],
});

Describing languages in a contextual promptYou can also name the expected languages in natural language as part of a contextual prompt (for example, Multilingual conversation in English, Spanish, and German.), but language_codes is the best-supported way to select languages. See Prompting and keyterms.

Supported languages

Universal-3.5 Pro Streaming code-switches across 18 languages.

Language	Code	Language	Code
English	`en`	Danish	`da`
Spanish	`es`	Finnish	`fi`
French	`fr`	Hindi	`hi`
German	`de`	Vietnamese	`vi`
Italian	`it`	Arabic	`ar`
Portuguese	`pt`	Hebrew	`he`
Turkish	`tr`	Japanese	`ja`
Dutch	`nl`	Mandarin	`zh`
Swedish	`sv`	Norwegian	`no`

Detecting the spoken language

Set the language_detection connection parameter to true to have each turn report which language was spoken. Turn messages then include language_code and language_confidence (a float between 0 and 1) fields, populated when an utterance is complete or the turn is final.

{
  "type": "Turn",
  "end_of_turn": true,
  "transcript": "¿Puedo pagar la factura por teléfono?",
  "language_code": "es",
  "language_confidence": 0.92
}

language_detection only controls reporting and doesn’t change how the model transcribes. It’s available on Universal-3.5 Pro Streaming and Universal-Streaming Multilingual.

Python
Python SDK
Javascript
JavaScript SDK

CONNECTION_PARAMS = {
    "sample_rate": 16000,
    "speech_model": "universal-3-5-pro",
    "language_detection": True,
}

client.connect(
    StreamingParameters(
        sample_rate=16000,
        speech_model="universal-3-5-pro",
        language_detection=True,
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-5-pro",
  language_detection: true,
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-5-pro",
  languageDetection: true,
});

Updating languages mid-stream

language_codes can be updated during an active session without reconnecting. This is useful when a voice agent detects the caller’s language, or when a conversation is handed off to a speaker of another language. Send an UpdateConfiguration message with the new values. The change takes effect from the next turn.

Python
Python SDK
Javascript
JavaScript SDK

# Steer transcription toward new languages
websocket.send('{"type": "UpdateConfiguration", "language_codes": ["en", "fr"]}')

# Clear steering and return to native code switching
websocket.send('{"type": "UpdateConfiguration", "language_codes": []}')

# Steer transcription toward new languages
client.update_configuration(language_codes=["en", "fr"])

# Clear steering and return to native code switching
client.update_configuration(language_codes=[])

// Steer transcription toward new languages
websocket.send(
  '{"type": "UpdateConfiguration", "language_codes": ["en", "fr"]}'
);

// Clear steering and return to native code switching
websocket.send('{"type": "UpdateConfiguration", "language_codes": []}');

// Steer transcription toward new languages
transcriber.updateConfiguration({ languageCodes: ["en", "fr"] });

// Clear steering and return to native code switching
transcriber.updateConfiguration({ languageCodes: [] });

See Updating configuration mid-stream for the full list of parameters you can update mid-stream.

Other streaming models

Universal-3.5 Pro Streaming is the only streaming model with native (mid-sentence) code switching. The other streaming models handle languages differently.

Model	Languages	Code switching
Universal-3.5 Pro Streaming	18 languages (see above)	Native, mid-sentence
Universal-Streaming Multilingual	`en`, `es`, `de`, `fr`, `pt`, `it`	Per turn
Universal-Streaming English	`en` only	No

See Select the speech model for a full model comparison.

Looking for pre-recorded code switching?

This guide covers code switching for streaming (real-time audio). If you’re working with pre-recorded audio, see Code Switching (Pre-recorded).

English <> French

English <> Hindi

English <> Mandarin

​Quickstart

​Steering toward known languages

​Supported languages

​Detecting the spoken language

​Updating languages mid-stream

​Other streaming models

​Looking for pre-recorded code switching?

Quickstart

Steering toward known languages

Supported languages

Detecting the spoken language

Updating languages mid-stream

Other streaming models

Looking for pre-recorded code switching?