Post-Cutoff
Search For AI agents

Google DeepMindGemini 3.5 familyCurrentSpeech and audioReleased 26 Aug 2026

Gemini 3.5 Transcribe (and Transcribe Live)

Google’s Gemini-based speech-to-text, successor in practice to Cloud Chirp 3 for developers.

Model idgemini-3.5-transcribe

Price$2 audio in, $12 out per 1M tokens

Checked29 September 2026

Where it stands

32newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

Before it from Google
Gemini 3.5 Live Translate9 Jun 2026
After it from Google
Gemini 3.8 Live15 Sep 2026
Weights
Closed weights; access is hosted only.

How to call it

3 ways to use Gemini 3.5 Transcribe (and Transcribe Live), with the model id each provider expects.

Providers, model ids, endpoints and docs for Gemini 3.5 Transcribe (and Transcribe Live)
ProviderModel idEndpointDocs
Gemini API (Interactions API, files) gemini-3.5-transcribe ai.google.dev
Gemini Live API (WebSocket streaming) gemini-3.5-transcribe-live ai.google.dev
Google AI Studio aistudio.google.com

Pricing

Prices for Gemini 3.5 Transcribe (and Transcribe Live)
Audio input$2 per 1M tokens
Output$12 per 1M tokens

As published: “per 1M tokens (USD) for gemini-3.5-transcribe (~$0.003/min audio in + ~$0.002/min text out); gemini-3.5-transcribe-live $3.50 in / $21.00 out (~$0.005 + ~$0.004 per min)”.

Source: ai.google.dev, checked 29 September 2026.

Specs

Input
Audio and text
Output
Text
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
26 August 2026
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Smart transcription

    Handles self-corrections, removes filler words and auto-formats text; custom vocabulary biasing up to 1,000 terms.

    Source: blog.google

  • Low word error rate

    Google cites Artificial Analysis WER of 2.6% (non-streaming) and 4.0% (streaming); 70% faster time-to-final than Chirp 3.

    Source: blog.google

  • 85+ languages with code-switching, diarization, word timestamps

    Utterance-level language detection across 85+ languages; speaker diarization; word-level timestamps (not combinable with custom vocabulary).

    Source: ai.google.dev

Notes

Changelog lists both ids GA on 2026-08-26, while the launch blog says public preview in AI Studio and Gemini Enterprise Agent Platform. Limits: 1 h per file request (30 min with diarization/timestamps), 10 min per live session. Diarization: docs say up to 8 speakers, blog says up to three - unresolved. Powers Rambler on Android and the Gemini app on macOS; coming to Chrome and Gboard. Press quotes $0.005/min (file) and $0.009/min (live) all-in. 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 lists hallucinations and occasional slowness/timeouts as limitations; surfaces: Antigravity, Gboard, Gemini app, Vertex AI, Google Workspace.

Sources: model page, pricing, changelog, launch blog.