Google’s new AI transcription edits out your ‘ums’ and ‘ahs’
Google updates Gemini Audio with new transcription capabilities that automatically detect specialized jargon and more than 85 languages. Gemini 3.5 Transcribe is a new addition to the Gemini family, improving precision and multilingual performance.
Intelligence analysis by Qwen 2.5 (3B)
Google has updated its Gemini Audio with new transcription models, including 3.5 Transcribe, which automatically detects specialized jargon and more than 85 languages, and removes filler words like 'um' and 'uh'.
Google made a new AI that can listen to people talk and write down what they say. It can understand different languages and remove the 'ums' and 'ahs' people say when they're talking.
Analysis
{"heading_1":"Improving Transcription Accuracy","paragraph_1":"Google’s Gemini Audio models have been updated with new transcription capabilities, including 3.5 Transcribe, which can automatically detect specialized jargon and more than 85 languages.","paragraph_2":"3.5 Transcribe is a new addition to the Gemini family, designed to improve precision and multilingual performance. It can automatically format text and remove filler words like 'um' and 'uh'.","paragraph_3":"Users can provide a customized vocabulary to the model, allowing it to adapt to unique spelling requirements and specialized jargon. It can also attribute speech for up to three speakers in pre-recorded audio, alongside providing word-level timestamps.","paragraph_4":"The new transcription model allows users to 'edit naturally with just your voice', according to Google. It can also attribute speech for up to three speakers in pre-recorded audio, alongside providing word-level timestamps.","paragraph_5":"These Gemini Audio updates are rolling out starting today in English for all macOS Gemini app users, and the Rambler dictation feature on Android in select countries and languages. It's also available for developers in public preview in the Gemini API via AI Studio and Antigravity.","paragraph_6":"Google says that Chrome support is coming soon. The updates are part of the company's efforts to improve the accuracy and naturalness of AI transcription, which could be beneficial for businesses and individuals using voice-controlled AI features."}
Key points
- Google updated its Gemini Audio with new transcription models
- 3.5 Transcribe is a new addition to the Gemini family
- It can automatically detect specialized jargon and more than 85 languages
- Users can provide a customized vocabulary to the model
- It can attribute speech for up to three speakers in pre-recorded audio
This new AI transcription could help people who need to write down what others say, like in meetings or interviews. It could also make it easier for people who are hard of hearing to understand what is being said.
There could be privacy concerns if this AI is used to record and transcribe private conversations without the people's consent.
