Google · Speech-to-Text
Gemini Live 3.5 Translate
Real-time speech-to-speech translation that processes audio continuously (not turn-by-turn), auto-detects input language, handles noise and preserves speaker intonation/pacing/pitch while staying a few seconds behind. 70+ languages / 2000+ pairs in one meeting via the Live API, AI Studio, Google Meet and Translate, with SynthID watermarking.
Open the source ↗Similar Audio & Speech releases
- MAI Playground
Microsoft AI · MAI Model Playground · Week 41, 2026
- Qwen3.8-LiveTranslate
Alibaba Qwen · Live Speech Translation · Week 39, 2026
- Speech-to-Speech
Hugging Face · Voice Agents · Week 31, 2026
- Sarvam Voice Agent with Pipecat
Sarvam AI · Voice Agents · Week 10, 2026
- UniAudio 2.0
Research · Text-to-Speech · Week 7, 2026
- Silero Models
Silero · Text-to-Speech · Week 3, 2026
More from Google
- Elephant-Goldfish Model (EGM)
Google · Agent design review · Week 45, 2026
- Colab in Google AI plans
Google · Cloud Notebooks · Week 44, 2026
- Gemini 3.8 Flash TTS
Google · Expressive Gemini TTS · Week 40, 2026
- Gemini 3.8 Live
Google · Live Voice Agent · Week 39, 2026
- Gemini 3.8 Flash and Flash Cyber
Google · Gemini 3.8 Flash · Week 36, 2026
- Gemini Agentic Video Understanding
Google · Agentic Video Understanding · Week 36, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.