ainewsblitz.com

Breaking

Google opens Gemini 3.5 Transcribe API for speech-to-text in 85-plus languages

  • Foundation Models
  • AI Agents

Google has put Gemini 3.5 Transcribe into public preview on the Gemini API, offering a dedicated speech-to-text model that automatically detects more than 85 languages, accepts custom vocabulary, and labels speakers on recorded audio. The company describes it as its most precise speech-to-text system yet and is aiming it at voice agents, live captioning, and post-call analytics.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,516 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year