# 9to5Google — Google launches Gemini 3.5 Transcribe, which powers Gboard Rambler & is coming to Chrome

- Company: 9to5Google (9to5google.com)
- Announced: 2026-08-26T17:00:00+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://9to5google.com/2026/08/26/gemini-3-5-transcribe/
- Record: https://forck.live/items/16991-google-launches-gemini-3-5-transcribe-which-powers-gboard-rambler-is-coming-to
- Subject: Reporting
- Models affected: Gemini 3.5 Transcribe, Chirp 3

Google introduced Gemini 3.5 Transcribe, a speech-to-text model that converts raw audio into formatted text, handling background noise, jargon, and filler words. It achieves a 4.0% word error rate for streaming and 2.6% for non-streaming, supports over 85 languages, and can identify up to three speakers. The model is in public preview for developers via the Gemini API and for enterprises via the Gemini Enterprise Agent Platform.

## Evidence

Verbatim from https://9to5google.com/2026/08/26/gemini-3-5-transcribe/:

> More precise transcription: As measured by Artificial Analysis, achieves an average Word Error Rate (WER) of 4.0% for streaming and 2.6% for non-streaming use-cases.

---

Record: https://forck.live/items/16991-google-launches-gemini-3-5-transcribe-which-powers-gboard-rambler-is-coming-to
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md