AI Briefing#transcription
The latest AI and developer news about #transcription, with the original source and a short summary.
The latest AI and developer news about #transcription, with the original source and a short summary.
The free, MIT-licensed desktop app runs Whisper and Llama.cpp locally to generate meeting summaries without adding a bot to calls.
The guide details using Scribe v2 for 98% accurate transcription and caption generation, supporting up to 32 speakers and 1,000 key terms.
Scribe v2 Realtime achieves 150 ms latency for live captioning, while batch Scribe v2 supports up to 1,000 keyword terms for accurate post-meeting transcripts.
The integration includes MAI-Voice-2.1, MAI-Voice-2.1-Flash, and MAI-Transcribe-2 Streaming with no platform fee or markup on inference.
The open-source multi-agent harness Munder Difflin v0.5.4 introduces a local transcription model that serves as an alternative to Whisper Flow and Granola.
ElevenLabs' Scribe v2 model supports over 90 languages and speaker diarization for up to 32 participants, exceeding Zoom's native 19-language post-meeting limit.
Google has released Gemini 3.5 Transcribe, a high-precision speech-to-text model that converts audio into clean text by handling background noise, technical jargon, and stuttering.
Google's Gemini 3.5 Transcribe model has been added to Vercel AI Gateway, supporting real-time and full-audio transcription.
A step-by-step guide to three methods for converting YouTube videos to text: built-in features, AI tools, and manual transcription.
AI email assistant Fyxer adopted ElevenLabs' Scribe v2, improving speaker identification accuracy in meeting notes and boosting user conversion rates.
A fine-tuned version of Cohere's open-source speech recognition model Transcribe has been released, adding speaker diarization and timestamp features.
Toothcomb has unveiled a real-time fact-checking tool that combines voice transcription and web search.
xAI has launched real-time and batch speech recognition and speech synthesis APIs.
Scribe V2 has launched new features that improve privacy protection, multilingual accuracy, and transcription quality.
ElevenLabs unveiled Scribe V2, a high-performance model for large-scale batch transcription and subtitle generation.
ElevenLabs has unveiled Productions, a human-edited content production agency service.
ElevenLabs has unveiled Scribe, an STT model supporting 99 languages with industry-leading accuracy.