Gemini 3.5 Live Translate is a verified current AI model with official specs, pricing or access details, capabilities, best use cases and key limitations.
Gemini 3.5 Live Translate is Google's low-latency speech-to-speech model for bidirectional realtime translation with natural audio output and transcript text.
Gemini 3.5 Live Translate is a current AI model verified from first-party Google sources.
Gemini 3.5 Live Translate is Google’s low-latency speech-to-speech model for bidirectional realtime translation with natural audio output and transcript text. Its verified context or usage limit is 131072 input tokens, with 65536 output tokens maximum output.
Paid audio pricing is $3.50/M input audio tokens and $21/M output audio tokens, equivalent to about $0.0368 per translated audio minute overall.
Live translation, Travel apps, Multilingual meetings, Contact centers, Realtime interpreter products.
No batch API, No grounding or tools, Preview availability can change.
In addition, its main capabilities include Realtime speech translation, 70+ languages, Audio-to-audio, Transcript output and Low-latency Live API. For example, common use cases include Interpreters, Meetings, Travel, Customer support and Voice apps.
In practice, this model may suit Live translation, Travel apps, Multilingual meetings, Contact centers and Realtime interpreter products. Also, notable strengths include 70+ languages, Natural speech output, Free tier and Low-latency design. However, review trade-offs such as No batch API, No grounding or tools and Preview availability can change before adopting it.
Meanwhile, Paid audio pricing is $3.50/M input audio tokens and $21/M output audio tokens, equivalent to about $0.0368 per translated audio minute overall. Effective combined audio cost is approximately $0.0368 per minute at the documented token rate.
Use the official model website, official documentation, pricing or release source and additional primary source to confirm current availability, limits and pricing. Product details can change after publication, so rely on primary documentation for final decisions.
Next, continue your research in the AI models directory, Google models and Realtime Translation Model models. Compare providers, pricing, modalities and practical limitations side by side to choose the right model for your workflow.
Translate this English speech to Hindi in realtime.Interpret this bilingual meeting naturally.Translate the caller while preserving conversational tone.Paid audio pricing is $3.50/M input audio tokens and $21/M output audio tokens, equivalent to about $0.0368 per translated audio minute overall.
A very current model with clear user interest around live multilingual voice translation and realtime AI applications.
