# Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a model from Google, released on 26 Aug 2026. The context window is 98,304 tokens. The maximum output is 32,768 tokens. Pricing is $2.00 (audio) per million input tokens and $12.00 (text) per million output tokens.

- Developer: Google
- Id: google/gemini-3.5-transcribe
- Reported: 2026-11-13T19:04:54.000Z
- Released: 2026-08-26T00:00:00.000Z
- Sighting: 2026-10-07T19:45:27.953Z
  - [evidence link](https://models.dev/#gemini-3.5-transcribe)
- Status: Released
- Canonical: https://alexgetman.com/models/google/gemini-3-5-transcribe-360/

## Questions

### What is the context window of Gemini 3.5 Transcribe?

The context window is 98,304 tokens. The maximum output is 32,768 tokens.

### How much does Gemini 3.5 Transcribe cost?

Pricing is $2.00 (audio) per million input tokens and $12.00 (text) per million output tokens.

### When was Gemini 3.5 Transcribe released?

On 26 Aug 2026.

- `gemini-3.5-transcribe` · standard · Input price: ≈ $0.003 / minute · /min* (audio)
- `gemini-3.5-transcribe` · standard · Output price (including thinking tokens): ≈ $0.002 / minute · /min* (text)
## Timeline

- 2026-11-13T19:10:15.656Z · [GitHub search · Google · pulls · mrojas54/maltese-agent · @dependabot[bot]](https://github.com/mrojas54/maltese-agent/pull/224)
> <li><strong>cli:</strong> use gemini-3.5-transcribe as default model for transcribe command (<a href="https://github.com/googleapis/js-genai/commit/df2994493dd07c0d9900e7c46e768e525abc6277">df29944</a>)</li>
**Confirmed use**
- 2026-11-13T20:30:39.709Z · [Google · official articles · Intelligent transcription with Gemini 3.5 Transcribe](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/)
> Pre-recorded audio processing: Transcribes recorded audio, meetings, call logs, and more with speaker attribution and word-level timestamps via the Interactions API using gemini-3.5-transcribe
**Confirmed use**
- 2026-11-13T20:30:39.709Z · [Google · official articles · Intelligent transcription with Gemini 3.5 Transcribe](https://deepmind.google/blog/intelligent-transcription-with-gemini-3-5-transcribe/)
> Pre-recorded audio processing: Transcribes recorded audio, meetings, call logs, and more with speaker attribution and word-level timestamps via the Interactions API using gemini-3.5-transcribe

## Evidence links

- [gemini-api-changelog](https://ai.google.dev/gemini-api/docs/changelog#08-26-2026)
- [review](https://aistudio.google.com/api-reference/models)
- [review](https://aistudio.google.com/docs/changelog)
- [gemini-model-index](https://aistudio.google.com/docs/models/gemini-3.5-transcribe)
- [gemini-pricing](https://aistudio.google.com/docs/pricing)
- [Google · official articles · Intelligent transcription with Gemini 3.5 Transcribe](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/)
- [vertex-google-models](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/gemini-3.5-transcribe)
- [Google · official articles · Intelligent transcription with Gemini 3.5 Transcribe](https://deepmind.google/blog/intelligent-transcription-with-gemini-3-5-transcribe/)
- [GitHub search · Google · pulls · mrojas54/maltese-agent · @dependabot[bot]](https://github.com/mrojas54/maltese-agent/pull/224)
- [models-dev](https://models.dev/#gemini-3.5-transcribe)

## Signals

- [Gemini 3.5 Transcribe spotted on Vertex AI](https://alexgetman.com/signals/2026/10/20/gemini-3-5-transcribe/)