Science and technology

Google launched Gemini 3.5 Transcribe for speech transcription. Belarusian is on the list

Google has introduced Gemini 3.5 Transcribe — a new speech recognition model. It supports over 85 languages, including Belarusian, and can clean text from filler words and self-corrections, writes Dev.by.

Google launched Gemini 3.5 Transcribe for speech transcription, Belarusian language is on the list

Unlike regular transcription, the model doesn't just literally record audio. For example, if a user says: "Let's meet on Tuesday — no, on Wednesday", the corrected version will remain in the final text. Gemini 3.5 Transcribe also automatically formats text and can take into account a user dictionary — for example, professional terms, names, or unusual spellings.

Two modes are available for developers. Gemini 3.5 Transcribe Live processes spoken language with a delay of less than a second and is designed for voice assistants, subtitles, and other real-time applications. The standard Gemini 3.5 Transcribe works with ready-made audio recordings — meetings, calls, and other files — and can add timestamps and identify speakers.

In recorded audio, the model can distinguish up to three interlocutors. Support for a larger number of speakers is currently in experimental mode.

According to independent service Artificial Analysis, the average rate of incorrectly recognized words in Gemini 3.5 Transcribe is 4% for streaming processing and 2.6% for working with ready-made recordings. Google also claims that the time to obtain a final transcription has been reduced by 70% compared to the previous Chirp 3 model.

Gemini 3.5 Transcribe is already used in several Google products. In the Gemini app for macOS, it allows dictating text, removing pauses and filler words, and executing voice commands taking into account screen content. In Gboard, the model underlies the Rambler feature, which converts free speech into formatted text and allows voice correction of what is written or changing the style.

In Google Antigravity, the model can consider screen content and chat history to more accurately recognize, for example, file names and terms from open documents. Developers can already try Gemini 3.5 Transcribe in public preview via the Gemini API in Google AI Studio and Google Antigravity. For enterprise customers, the model is available through the Gemini Enterprise Agent Platform.

Comments

Now reading

Zelenskyy: Ukraine closes Russian sky for civilian aviation 8

Zelenskyy: Ukraine closes Russian sky for civilian aviation

All news →
All news

Tim Cook steps down as Apple CEO after 15 years of leadership

Young lawyer Miroslav Bandarenka sentenced for politics and declared a "terrorist" 2

21-year-old man sought in Dzyarzhynsk district found dead

Air raid alarms sounded and NATO fighters scrambled in Romania, Estonia, and Latvia due to drones

22-year-old BMW driver knocked down a lighting mast on MKAD 4

"I don't know where he lives or what he eats." Husband took son from Belarusian model in Canada 19

«How much did you get paid for the ad?» Young Man with Model Looks Makes Top TikToks from His Job at a Lift Factory 5

"Waiting for +1 landmark in Minsk!" Bloggers brought to former Valadarsky Street prison 22

Ministry of Justice revokes lawyer's license for discrediting actions

больш чытаных навін
больш лайканых навін

Zelenskyy: Ukraine closes Russian sky for civilian aviation 8

Zelenskyy: Ukraine closes Russian sky for civilian aviation

Main
All news →

Заўвага:

 

 

 

 

Закрыць Паведаміць