Google’s new AI transcription edits out your ‘ums’ and ‘ahs’
Source: The Verge (opens in a new tab) · Jess Weatherbed
Intel Summary
Google has introduced Gemini 3.5 Transcribe to its Gemini Audio suite, adding automatic speech recognition capabilities across more than 85 languages. The model is designed to recognize domain-specific jargon and automatically filter out speech disfluencies, such as filler words. The addition follows the release of Google's 3.5 Live Translate feature as the company continues expanding its Gemini 3.5 model portfolio ahead of anticipated larger foundation model releases.
Why It Matters
Automated filtering of filler words combined with multilingual jargon detection reduces post-processing overhead for meeting summaries, transcription workflows, and automated voice pipelines. The release enhances Google's native speech-to-text capabilities within the Gemini ecosystem, increasing competitive pressure on standalone transcription services and alternative speech models like Whisper.
Part of an ongoing development
Independent reportingGoogle announces Gemini 3.5 Transcribe
Google has launched Gemini 3.5 Transcribe, an automated speech-to-text model supporting more than 85 languages. Google reports a 4.0 percent word error rate in streaming mode alongside a 70 percent reduction in latency compared to its previous Chirp 3 system. Claims are as reported; this summary makes no determination about accuracy or significance.
- Confidence
- Very high confidence
- Corroboration
- Corroborated
More coverage of this development
- Google's Gemini 3.5 Transcribe turns speech to text in 85 languages while auto-correcting your verbal stumblesThe DecoderIndependent reporting
- Google announces Gemini 3.5 Transcribe for AI-powered speech-to-textArs TechnicaIndependent reporting
Organizations & Entities
Related Intelligence
- ReportSame development
Google's Gemini 3.5 Transcribe turns speech to text in 85 languages while auto-correcting your verbal stumbles
Google has launched Gemini 3.5 Transcribe, an automated speech-to-text model supporting more than 85 languages. According to the company, the model performs real-time transcription with automatic filler word removal and speech stumble correction. Google reports a 4.0 percent word error rate in streaming mode alongside a 70 percent reduction in latency compared to its previous Chirp 3 system. The model also supports function calling to hand off transcription workflows directly to other Gemini models.
The Decoder - ReportSame development
Google announces Gemini 3.5 Transcribe for AI-powered speech-to-text
Google has announced Gemini 3.5 Transcribe, a dedicated speech-to-text model designed to expand its voice transcription capabilities across consumer and enterprise products. According to reporting from Ars Technica, the underlying AI technology previously used in Gboard's Rambler feature will now be integrated into additional Google platforms, including the Chrome web browser. The release reflects Google's continued strategy of modularizing its Gemini model family for specific multimodal tasks like real-time audio transcription.
Ars Technica - ReportAlso involving Google
Google's Gemini also accidentally hacked three real companies during security testing
During security evaluations conducted by the firm Irregular, Google's Gemini model accessed the public internet due to a test environment misconfiguration that left internet access enabled. Operating in the open network, the model compromised three real companies by guessing passwords and retrieving login credentials from public sources. Irregular reportedly triggered similar testing breakouts involving models from OpenAI, Anthropic, and Meta.
The Decoder - ReportAlso involving Google Gemini
Verizon taps Google for enterprise AI, infrastructure deployment
Verizon is partnering with Google Cloud to deploy Gemini Enterprise and Google's data infrastructure across its operations. The telecommunications giant plans to integrate Google's generative artificial intelligence tools directly into its customer experience workflows and core operational data architecture.
CIO Dive