Gemini 3.5 Transcribe Live
Gemini 3.5 Transcribe Live converts speech into text as audio arrives, returning partial and final transcripts through a bidirectional WebSocket connection. Its sibling Gemini 3.5 Transcribe handles prerecorded audio as a complete file in a single request. Summary written by AI Index from Google’s own pages.
- Streaming
Prices
2 offerings · prices as listed Gemini API (opens in a new tab)
gemini-3.5-transcribe-live| Conditions/ 1M tokens | Input | Output |
|---|---|---|
| Text tokens Standard | — | $21.00 |
| Audio tokens | $3.50 | — |
Prices from Gemini API pricing (opens in a new tab) (checked Nov 8, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Speaker diarization
- —
- Timestamps
- —
- Model ID
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers speech recognition yet. We will cite one when its license allows.
News
All news →- Nov 17, 2026Capability Google adds voice editing to Gemini 3.5 Transcribe Gemini 3.5 Transcribe and Gemini 3.5 Transcribe Live now support voice-driven editing, rewriting, and formatting of dictated speech or existing text.
- Aug 26, 2026Release Google releases Gemini 3.5 Transcribe Live Gemini 3.5 Transcribe Live is now available.
Changes
All changes →- Now priced on Google Cloud Vertex AI Input (Audio tokens) $3.50 · Output (Text tokens) $21.00
- New speech to text model
Sources
- Gemini API pricing (opens in a new tab) ai.google.dev · checked Nov 8, 2026
- Gemini 3.5 Transcribe Live model (opens in a new tab) ai.google.dev · checked Nov 3, 2026
- Gemini API changelog (opens in a new tab) ai.google.dev · checked Nov 8, 2026
- Vertex AI generative AI pricing (opens in a new tab) cloud.google.com · checked Nov 3, 2026
Google’s official policies: data use, privacy, terms →
Google · United States · ai.google.dev
Related models
Snapshots, the same family and other models from this provider