Demis Hassabis retweets: Gemini 3.5 Transcribe launch, multi-speaker support
demishassabis · x · 2026-08-27
Demis Hassabis retweets Sundar Pichai's post about Gemini 3.5 Transcribe, highlighting multi-speaker recognition, 85+ language auto-detection, and custom vocabulary adaptation. API available in Google AI Studio and Gemini Enterprise.
Related event: Google Launches Gemini 3.5 Transcribe Speech-to-Text Model(17 posts)→
More from Multimodal
- Open-source AI video project hits 42k stars: one prompt to finished video, clones viral hits — Vjeux · 2026-08-27
- AI-generated anime: Robert's Rebellion from A Song of Ice and Fire — XCaliber_000 · 2026-08-27
- Visual video on Cinema Structures — listopalafoto · 2026-08-27
- Dev builds a ComfyUI node that truly frees VRAM via the internal /api/free endpoint — JustLookingForNothin · 2026-08-27
- Original AI-generated music video: "I Fell in Love Again" — johnstro12 · 2026-08-27
- ByteDance's DiffusionOPSD: new distillation method with open LoRAs for Z-Image-Turbo and SD-3.5 — AgeNo5351 · 2026-08-27