Google AI Edge Eloquent: Free Offline AI Dictation Arrives on iOS
Google launches a free, offline-first AI dictation app that automatically polishes speech and removes filler words??o subscription required.
Tag: ASR
Cohere Transcribe: The Open-Weight ASR Model That Outperforms Whisper with 5.42% Word Error Rate
Cohere's new open-weight ASR model Transcribe achieves 5.42% WER, outperforming Whisper and ElevenLabs, with full commercial deployment flexibility under Apache-2.0 license.
Microsoft’s VibeVoice Is the Open-Source Voice AI Platform That Runs Entirely on Your Hardware
Microsoft releases VibeVoice, an open-source frontier voice AI framework with 60-minute speech recognition, 90-minute TTS, and real-time models — all downloadable and runnable entirely on-premises.
Microsoft Releases VibeVoice: A New Open-Source Frontier Voice AI Framework
Microsoft has unveiled VibeVoice, an open-source voice AI framework featuring state-of-the-art speech recognition and synthesis capabilities including 60-minute audio processing and multi-speaker support.
Microsoft VibeVoice: The Open-Source Frontier Voice AI That Transcribes an Hour of Audio in One Pass
Microsoft has open-sourced VibeVoice, a comprehensive voice AI framework featuring a 7B-parameter speech recognition model that processes 60-minute audio in a single pass, multilingual support across 50+ languages, and native integration with…
Microsoft Releases VibeVoice: A New Open-Source Frontier Voice AI Framework
Microsoft has unveiled VibeVoice, an open-source voice AI framework featuring state-of-the-art speech recognition and synthesis capabilities including 60-minute audio processing and multi-speaker support.
Microsoft VibeVoice: Open-Source Frontier Voice AI Goes Mainstream
Microsoft's VibeVoice speech AI family now includes ASR, TTS, and real-time voice synthesis — all open-source. With integration into Hugging Face Transformers, it's bringing frontier voice AI to the mainstream developer community.
