---
format: "aidr-story-markdown/v1"
id: "11534d86499a05550d81989e99efe4e23006536abe8561e6ac7c2d3e32d965d6"
canonical_url: "https://aidr.today/11534d86?lang=en"
title: "Google Ships Gemini 3.5 Transcribe to Cut Transcription Time 70% Over Chirp 3"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-26T19:04:30.000Z"
category: "Models"
topics: ["google","gemini","llm","inference"]
source_urls: ["https://huggingnews.com/ai/google-ships-gemini-35-transcribe-to-cut-transcription-time-70percent-ov-25c56bda","https://x.com/Google/status/2092659278632894576","https://x.com/sundarpichai/status/2092659467284517088","https://x.com/OfficialLoganK/status/2092660925509890397","https://x.com/_philschmid/status/2092659659866030112","https://x.com/Google/status/2092659286182699139","https://x.com/Google/status/2092659284349682024"]
summary: "Google released its most precise speech-to-text model, Gemini 3.5 Transcribe, which automatically removes filler words and supports more than 85 languages. The tool is integrated into the Gemini app for macOS and the Rambler feature on Android, with developer access provided via Google AI Studio and the Gemini API. The model achieves a 2.6% word error rate on non-streaming audio and 4% on streaming, reflecting a 70% reduction in final transcription time compared to the previous Chirp 3. It provides speaker attribution for up to three people and offers sub-second bidirectional streaming through the Gemini Live API to handle alphanumeric tokens such as postal codes and order IDs."
---

# Google Ships Gemini 3\.5 Transcribe to Cut Transcription Time 70% Over Chirp 3

> [Open the canonical story](<https://aidr.today/11534d86?lang=en>)

**Published:** 2026-08-26T19:04:30.000Z
**Category:** Models
**Topics:** google, gemini, llm, inference

## Summary

Google released its most precise speech\-to\-text model, Gemini 3\.5 Transcribe, which automatically removes filler words and supports more than 85 languages\. The tool is integrated into the Gemini app for macOS and the Rambler feature on Android, with developer access provided via Google AI Studio and the Gemini API\. The model achieves a 2\.6% word error rate on non\-streaming audio and 4% on streaming, reflecting a 70% reduction in final transcription time compared to the previous Chirp 3\. It provides speaker attribution for up to three people and offers sub\-second bidirectional streaming through the Gemini Live API to handle alphanumeric tokens such as postal codes and order IDs\.

## Sources

- [Story source](<https://huggingnews.com/ai/google-ships-gemini-35-transcribe-to-cut-transcription-time-70percent-ov-25c56bda>)
- [Story source](<https://x.com/Google/status/2092659278632894576>)
- [Story source](<https://x.com/sundarpichai/status/2092659467284517088>)
- [Supporting source](<https://x.com/OfficialLoganK/status/2092660925509890397>)
- [Supporting source](<https://x.com/_philschmid/status/2092659659866030112>)
- [Supporting source](<https://x.com/Google/status/2092659286182699139>)
- [Supporting source](<https://x.com/Google/status/2092659284349682024>)