Convert to text · See the tone · Fully local
mubai-ears
@HMH323
Equip your AI companion with ears—local speech transcription + prosody analysis.
mubai-ears turns a piece of speech into timed text, sound graphs, and numerical summaries at the same time. AI can read the content of the speech, and can also refer to the pitch, volume, pauses and speed of speech to understand how the sentence was said.
Project address (can be copied to AI):https://github.com/hmh323/mubai-ears
PROJECT INTRO
Project introduction
mubai-ears is a small tool for AI companions to process speech. One part of it is responsible for converting speech into text with time, and the other part is responsible for organizing the pitch, severity, pause and speed of the sound into pictures and numbers.
By handing these results to an image-enabled AI, it can see both "what was said" and "how it was said," allowing it to better understand the tone and rhythm of the moment. The entire process is completed on the user's own computer.
- Suitable for:People who want an AI companion to understand the content of speech, taking into account tone, pauses, and rhythm.
- will generate:Timed text, sound charts, and summaries of pitch, volume, pauses, and speaking rate.
- Supported formats:can process wav, and can also read common audio such as webm, m4a and mp3 through ffmpeg.
- Usage:This is a Python tool that needs to be run on a computer, not a complete voice chat application.
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...