Microsoft releases free voice input tool Vibing, based on their VibeVoice model, competing with the paid product WisprFlow.

robot
Abstract generation in progress

According to 1M AI News monitoring, Microsoft has released a desktop voice input tool called Vibing, based on its own open-source speech AI model VibeVoice. It supports macOS and Windows and is free to use. Press the keyboard shortcut (Mac: right Option / Windows: Ctrl+Win) to bring up recording in any application, and afterward it automatically outputs the text. After personally testing it, AI/ML community reviewer @realmrfakename said the transcription is accurate and fast, and rated it as a “free alternative to WisprFlow.”

Vibing isn’t just speech-to-text. Using an LLM, it rewrites spoken language into written text suitable for the current context, and supports using natural language to directly modify, delete, and reorganize existing content during input. Other features include continuous recording for a single session longer than 5 minutes, automatic recognition of 50+ languages, mixed Chinese-English input within the same sentence, custom hot words, and real-time translation.

At the core is Microsoft’s VibeVoice, an open-source speech AI model family under the MIT license. It has more than 28,000 GitHub stars and includes a 7B-parameter ASR model (processes 60 minutes of audio per session), a 1.5B TTS model (generates 90 minutes of multi-speaker voice), and a 0.5B real-time model (300ms latency). WisprFlow is one of the most popular AI voice input tools on Mac, charging via monthly subscription; Vibing enters the same arena directly with a free + open-source approach.

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin