Gemini 3.5 Transcribe (and Transcribe Live)
Speech and audio
gemini-3.5-transcribe
$2 audio in, $12 out per 1M tokens
Gemini 3.5 Live Translate
Model idgemini-3.5-live-translate-preview
Price$3.50 audio in, $21 audio out per 1M tokens
Checked29 September 2026
Where it stands
52newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- Before it from Google
- Gemini 3.1 Flash TTS (preview)15 Apr 2026
- After it from Google
- Gemini 3.5 Transcribe (and Transcribe Live)26 Aug 2026
- Weights
- Closed weights; access is hosted only.
How to call it
3 ways to use Gemini 3.5 Live Translate, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Gemini Live API (WebSocket) | gemini-3.5-live-translate-preview |
ai.google.dev | |
| Google AI Studio | aistudio.google.com | ||
| Google Translate app / Google Meet | translate.google.com |
Pricing
| Audio input | $3.50 per 1M tokens |
|---|---|
| Audio output | $21 per 1M tokens |
As published: “per 1M tokens (USD); ~$0.0053/min audio in, ~$0.0315/min audio out”.
Source: ai.google.dev, checked 29 September 2026.
Specs
- Input
- Audio
- Output
- Audio and text
- Context window
- 131,072 tokens
- Max output
- 65,536 tokens
- Open weights
- No
- Licence
- Proprietary
- Released
- 9 June 2026
- Status
- Preview
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Continuous speech-to-speech translation preserving the speaker’s voice
Audio-to-audio (no ASR-MT-TTS cascade), generating speech continuously a few seconds behind the speaker while keeping intonation, pacing and pitch.
70+ languages, 2,000+ pairs
Auto-detects 70+ languages and supports 2,000+ language combinations in one meeting; expands Google Meet live translation from 5 to 70+ languages.
Notes
Public preview in the Live API/AI Studio from 2026-06-09; Meet private preview; Google Translate on Android/iOS (incl. headphone ‘listening mode’). Outputs SynthID-watermarked. No function calling, thinking or caching. Model card (read 2026-09-29): https://deepmind.google/models/model-cards/gemini-3-5-audio/ - covers Gemini 3.5 Live Translate, Transcribe and Transcribe Live (card dated 2026-08-26); no numeric evals in the card itself; knowledge cutoff January 2025; did not reach any Tracked or Critical Capability Levels under the Frontier Safety Framework. Card-listed Live Translate limitations: inconsistent voices, language detection struggles with non-native accents and rapid switching, imperfect background-noise handling, occasional audio artifacts. OpenAI’s rival gpt-realtime-translate launched a month earlier (2026-05-07).
Sources: model page, pricing, launch blog.