Activefastmultimodal Proprietary

Gemini 3.5 Live Translate

by Google

Gemini 3.5 Live Translate is a specialized model from Google designed for real-time speech translation and transcription. It combines low-latency streaming with high accuracy across multiple languages, making it ideal for live conversations and events. This model is part of Google's Gemini family, optimized for speed and efficiency in translation tasks.

Official Site API Docs

Input cost

$0.50 per 1M tokens

Output cost

$1.50 per 1M tokens

Context window

32K tokens

Max output

4096 tokens

Modalities

textaudio

License

proprietary

Capabilities

Real-time Speech TranslationSpeech TranscriptionStreamingMulti-language SupportLow Latency

Best For

Real-time speech translation and transcription for live conversations and events.

Strengths

Very low latency for real-time use
High accuracy in speech translation
Supports multiple languages
Optimized for streaming audio

Limitations

Limited to speech translation tasks
Smaller context window than general Gemini models
May not handle complex text generation well
Pricing can be higher for high-volume streaming

Use Cases

Live conference interpretation

Real-time subtitling for broadcasts

Voice translation in customer support

Transcription and translation of meetings

Language learning with instant feedback

Accessibility for deaf or hard-of-hearing users

Multilingual live streaming

Back to all models