PulseAugur
EN
LIVE 01:53:07
日本語(JA) 「えー」「あー」を除去して複数話者音声文字変換「Gemini 3.5 Transcribe」 https://www. watch.impress.co.jp/docs/news/ 2136424.html # watch_impress # Google # Gemini # テック # AI

Google releases Gemini 3.5 Transcribe for cleaner audio transcription

By PulseAugur Editorial · [2 sources] ·

Google has released Gemini 3.5 Transcribe, a new speech-to-text model designed to automatically remove filler words like "uh" and "um" from audio recordings. This model also features multi-speaker diarization, allowing it to distinguish between different speakers in a conversation. The technology aims to streamline the transcription process for various applications. AI

IMPACT Streamlines audio transcription by removing filler words and identifying speakers, potentially improving efficiency for content creators and researchers.

RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Google releases Gemini 3.5 Transcribe for cleaner audio transcription

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
product, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
44 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. Mastodon — mastodon.social TIER_1 日本語(JA) · [email protected] ·

    Speech recognition model "Gemini 3.5 Transcribe" that can automatically remove "uh" and "ah" https:// pc.watch.impress.co.jp/docs/ne ws/2136518.html # impress # market # AI # Gemini

    「えーと」や「あー」を自動除去できる音声認識モデル「Gemini 3.5 Transcribe」 https:// pc.watch.impress.co.jp/docs/ne ws/2136518.html # impress # 市場 # AI # Gemini

    LINKS pc.watch.impress.co.jp/…/2136518.html
  2. Mastodon — mastodon.social TIER_1 日本語(JA) · [email protected] ·

    Speech-to-text for multiple speakers with removal of "uh" and "um" using Gemini 3.5 Transcribe https://www.watch.impress.co.jp/docs/news/136424.html #watch_impress #Google #Gemini #Tech #AI

    「えー」「あー」を除去して複数話者音声文字変換「Gemini 3.5 Transcribe」 https://www. watch.impress.co.jp/docs/news/ 2136424.html # watch_impress # Google # Gemini # テック # AI

    LINKS watch.impress.co.jp/…/2136424.html

RELATED ENTITIES

RELATED TOPICS