Tag
Meta has released Muse Voice Transcribe, a real-time speech-to-text model with a 3.1% word error rate and adaptive streaming capabilities, making it suitable for voice agents.
A tweet from Andrew Chen asking about setting up a Bluetooth ring to trigger voice transcription, mentioning WisprFlow.
Ink-2 ranked #2 on the new VoiceCodeBench benchmark, demonstrating its suitability for real-time consumer apps, with GPT Live Transcribe taking the #1 spot.
LM Studio launches Bionic, an AI agent for open models that supports coding, document work, and offline voice transcription, with flexible model execution and zero data retention.
Successfully reverse-engineered Wispr Flow's transcription protocol and open-sourced a standalone Node client, reusing its login state and directly calling the backend gRPC transcription service.
The article explains how to implement ASR biasing for voice transcription models, using examples from Groq and local models, and introduces the open-source Freestyle project that incorporates this feature.
Whisper Island by Coddo is a macOS application that provides voice transcription directly within the Mac's notch area.