Radio
Now Playing
Quickyla Radio โ€” Click to play
Open โ†’
3 min left

Google says its latest Gemini transcription model can turn your ramblings into structured text

The company says Gemini 3.5 Transcribe will soon let you use speech-to-text in any web field in Chrome. Google has revealed a new AI audio model that it says offers improved speech recognition and tโ€ฆ

Google says its latest Gemini transcription model can turn your ramblings into structured text
Engadget โ€” 26 August 2026
Text:
3 0 0

The company says Gemini 3.5 Transcribe will soon let you use speech-to-text in any web field in Chrome.

Google has revealed a new AI audio model that it says offers improved speech recognition and transcription.ย The company says Gemini 3.5 Transcribe is more adept at speech-to-text than earlier models, with greater precision and the ability to automatically detect more than 85 languages. It says the model can adapt a user's unstructured speech into formatted text. You can use it to make edits with voice commands, andย it removes filler words from transcribed speech too.

Instead of typing out every thought, Gemini 3.5 Transcribe works with the way you actually talk:

โœ… Seamlessly handles self-corrections โœจ Removes filler words to deliver clean, formatted text ๐ŸŽฏ Understands your natural intent and speaking style ๐Ÿ”Š Accurately captures audio in... pic.twitter.com/17YcsDi7Q0

Google says the model can learn custom vocabulary and unique spellings, and is adept at capturing alphanumeric strings such as order numbers and postal codes. Moreover, the company claims Gemini 3.5 Transcribe can attribute speech to up to three speakers with word-level timestamps based on pre-recorded audio. That could be handy for, say, transcribing a podcast.

It may not come as a surprise that Gemini 3.5 Transcribe powers the Rambler feature on Android devices like the Pixel 11-series phones as well as the Gemini app on macOS (where it can work with other Gemini models to carry out agentic tasks).

Intriguingly, Google says you'll soon be able to use text-to-speech in any field on a web page in Chrome. For instance, you'll be able to dictate replies and posts, and use your voice to prompt Gemini. Gemini 3.5 Transcribe is also available in Google Antigravity, the company's agentic development platform, and it's coming to Search Live, Gemini Live, Docs, Keep and Gmail. Developers will be able to tap into the model via APIs.

Update, August 26, 2026, 2:05PM ET: Updated to remove some information Google has not yet publicly announced.

Read Full Story at Engadget โ†’
Advertisement
React:
Sources
Sponsored

More to Read

Google announces Tensor G6, bringing 4K Portrait Video and โ€ฆ
๐Ÿ’ป Technology
Google announces Tensor G6, bringing 4K Portrait Video and more to the Pixel 11 series
Android Authority ยท 14 days ago
Apple announces Ultra 4 and Series 12 Watch models for nextโ€ฆ
๐Ÿ’ป Technology
Apple announces Ultra 4 and Series 12 Watch models for next month
9to5Mac ยท 12 days ago
Sony says the 3.5mm headphone jack is still a hit, and its โ€ฆ
๐Ÿ’ป Technology
Sony says the 3.5mm headphone jack is still a hit, and its phone sales back it up
Android Authority ยท 13 days ago
Iran voids 60-day nuclear negotiation deadline with US
๐ŸŒ World News
Iran voids 60-day nuclear negotiation deadline with US
France 24 ยท 8 days ago
Idlib residents celebrate court's death sentence for Assad,โ€ฆ
โš”๏ธ War & Conflict
Idlib residents celebrate court's death sentence for Assad, former officials
Al Jazeera ยท 14 days ago
Iran demands U.S. recognize defeat in Strait of Hormuz tensโ€ฆ
๐Ÿ›๏ธ Politics
Iran demands U.S. recognize defeat in Strait of Hormuz tensions
NBC News ยท 10 days ago
Full view