Demo shows Gemini 3.5 Transcribe features smart rewrite and custom vocabulary
patloeber · x · 2026-08-27
Twitter user @thorwebdev shared a demo of Gemini 3.5 Transcribe. The model is positioned as the most precise STT tool yet, featuring: intent-based smart text rewriting and formatting; support for 85+ languages and accents; custom vocabulary for jargon; high precision in alphanumerics; and multi-speaker identification.
More from Multimodal
- HeyGen Open Sources HyperFrames to Enable AI Video Editing via Code — altryne · 2026-08-27
- Seedance 2.5 integrated into Magnific with native audio-video sync — LudovicCreator · 2026-08-27
- Seedance 2.5 Generates Audio/Video in One Pass, Uses Native Low-Res to Cut Costs — LudovicCreator · 2026-08-27
- Seedance 2.5 Supports 50 Reference Assets to Solve Character Consistency — LudovicCreator · 2026-08-27
- 7-Step Roadmap: Building Multimodal AI Agents from LLMs to Grounded Systems — MaryamMiradi · 2026-08-27
- Descript details specialized models for zero-shot speech fix and lip sync — descript · 2026-08-27