Model Releases

Gemini 3.5 Transcribe launches as a high-accuracy speech-to-text model for real-time voice interaction

Original title:Intelligent transcription with Gemini 3.5 Transcribe

AI summary

Google DeepMind introduced Gemini 3.5 Transcribe, a speech-to-text model supporting both streaming and non-streaming APIs. According to Artificial Analysis benchmarks, its average word error rates are 4.0% for streaming and 2.6% for non-streaming, with support for over 85 languages, custom vocabulary and speaker identification for up to three speakers.

Key Takeaways

  • Google DeepMind introduced Gemini 3.
  • 5 Transcribe,a speech-to-text model supporting both streaming and non-streaming APIs.
  • According to Artificial Analysis benchmarks,its average word error rates are 4.
  • 0% for streaming and 2.
  • 6% for non-streaming,with support for over 85 languages,custom vocabulary and speaker…

Quick Facts

Published
Updated
Source
Google DeepMind:Blog(RSS)
Category
Model Releases
AI score
68
Read the original Read the full article at the original source
Why it matters

相较于上一代 Chirp 3,流式词错率降到 4.0% 且最终转录延迟改善 70%,会影响语音代理和实时字幕方案的成本与体验取舍。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Gemini 3.5 Transcribe launches as a high-accuracy speech-to-text model for real-time voice interaction. August 27, 2026. https://new.nat6.net/en/news/cmtacq8vz0aedroj24bcix9go/

View all →