Google Releases Gemini 3.5 Live Translate, a Streaming Speech-to-Speech Audio Model Covering 70+ Languages Across Meet, Translate, and the Live API

Google just announced Gemini 3.5 Live Translate. It is their latest audio model for live speech-to-speech translation. Speech-to-speech means spoken audio goes in, and translated spoken audio comes out. The model detects over 70 languages automatically and generates translated speech. It preserves the speaker’s intonation, pacing, and pitch in the output. Turn-by-turn systems wait for a speaker to finish before responding. Gemini 3.5 Live Translate generates speech continuously instead. It balances a trade-off between waiting for context and translating immediately. More context improves quality. Faster output keeps the translation in sync with the speaker. The result stays a few seconds behind the speaker throughout a session.

Gemini 3.5 Live Translate is a single audio model (gemini-3.5-live-translate-preview), not a chat assistant. It processes speech as the audio streams in, rather than after a full sentence. It handles multilingual inputs without manually configuring settings. Its noise robustness lets applications run in loud, unpredictable environments.

The model is rolling out across three surfaces. Developers get it in public preview through the Gemini Live API and Google AI Studio. Enterprises get a private preview in Google Meet starting this month. Everyone else gets it through the Google Translate app on Android and iOS.

How the Continuous Streaming Works

The design difference matters for building real-time features. A conversational Live agent uses turn-based interactions. It relies on pauses, intent detection, and interruption handling. Live Translation uses continuous stream processing instead. It translates as the speaker talks, without waiting for turns to end.

To hold strict real-time latency thresholds, the translation path accepts audio input only. Text input is not supported in translation mode. The model also drops tool use and system instructions in this mode. That keeps it a focused translator pipeline rather than a general agent.

Building With the Live API

Developers configure translation inside the Live API session setup. You set a translationConfig block within the generationConfig. The targetLanguageCode field takes a BCP-47 code, such as "pl" or "es". BCP-47 is the standard format for language tags like en or pt-BR. It defaults to "en". The echoTargetLanguage boolean controls input that is already in the target language. When true, the model echoes that speech. When false, it stays silent. You can also enable inputAudioTranscription and outputAudioTranscription for text transcripts.

Audio formats are fixed. Input is raw 16-bit PCM at 16kHz, mono, little-endian. Output is raw 16-bit PCM at 24kHz, mono, little-endian. PCM is uncompressed raw audio. You send audio in chunks of 100ms. For client-side apps, ephemeral tokens on the v1alpha endpoint avoid exposing your API key.

Dimension	Live Agent	Live Translation
Model role	Assistant that listens, reasons, and acts	Interpreter / real-time translator pipeline
Interaction	Turn-based, with interruption handling	Continuous stream processing, no turns
Tools	Function calling, Google Search, instructions	Translation only, no tools or instructions
Inputs	Text, audio, video, and image	Audio only, for strict latency
Configuration	Generation, speech, tools, instructions	targetLanguageCode and echoTargetLanguage

---

Use Case

The model targets live interpretation across several settings. Google lists multilingual calls, meetings, lessons, and broadcasts. Developer platforms reduce the integration work for real-time media. Agora, Fishjam, LiveKit, Pipecat, and Vision Agents already use the Live API. These platforms handle the complex real-time media streaming infrastructure. That lets developers focus on the user experience instead.

Google’s example app demonstrates dubbing and simultaneous multi-language translation. Grab is testing the model for driver-and-traveler communication at pickups. Grab users make over 10 million voice calls per month. CJ ENM, LiveKit, and others reported positive feedback on quality, accuracy, and low latency.

How It Changes Google Meet and Translate

According to Google’s official release, Google Meet will soon use 3.5 Live Translate for speech translation. The table shows the stated before-and-after for Meet.

Capability	Previous Meet	With 3.5 Live Translate
Languages	5	70+
Combinations per meeting	Only to and from English	2000+ combinations
Access	Existing interface	Updated interface for instant access

The Meet update is in private preview for select business Workspace customers this month. A broader rollout follows later this year. In the Translate app, the Live translate feature works with any connected headphones. It mirrors the speaker’s tone across 70+ languages. Android also gains a listening mode. You hold the phone to your ear like a regular call. The translated audio then streams through the earpiece, without others hearing.

Key Takeaways

• Gemini 3.5 Live Translate is Google’s latest audio model for live speech-to-speech translation across 70+ languages.
• It streams continuously instead of turn-by-turn, staying a few seconds behind the speaker.
• Developers can configure it via the Live API using targetLanguageCode and echoTargetLanguage; audio-only, 16kHz in, 24kHz out.
• It rolls out to the Gemini Live API, Google Meet (5→70+ languages), and the Translate app.
• All generated audio carries an imperceptible SynthID watermark for detectability.

---

Need to partner with us for promoting your GitHub Repo OR Hugging Face Page OR Product Release OR Webinar etc.? Connect with us