AI Meeting Notes with Speaker Labels (Free)
Record or drop a meeting recording to get a transcript split by speaker plus an automatic summary of key sentences, to-dos and decisions. Files stay on your device.
- Only upload files you have the right to use. Copying or sharing other people's music, videos or recordings without permission can violate copyright law. FreeSoundTools does not store your files on a server.
- Don't upload secret recordings of conversations you were not part of. Recording other people without consent can be illegal.
Loading the tool...
Paid meeting assistants usually upload your audio to their servers. Here, Whisper speech recognition and the pyannote speaker model run inside your browser.
When to use it
- Make minutes of a team meeting or interview
- Separate who said what in a two- to five-person conversation
- Pull out to-dos and decisions from a long call
How to use
- Choose a model, language (English by default) and the number of speakers, or leave it on auto.
- Drop a recording or record with your microphone.
- Wait for transcription and speaker labeling.
- Rename speakers, merge two speakers if they were split, and refresh the summary.
- Save as Word (DOCX), Markdown, SRT or TXT.
Supported formats and limits
- Input: mp3 · m4a · wav · webm · mp4 and more, or live mic recording
- Models: Whisper tiny/base/small plus the pyannote segmentation model (about 2MB)
- Speakers: auto, or 2 to 5
- Summary is rule-based (key sentences, keywords, possible to-dos and decisions), for reference only
Tips
- Ask everyone for consent before recording.
- Speaker labels are less accurate with overlapping speech or background noise.
FAQ
Is my recording uploaded?
No. Transcription and speaker labeling run in your browser; only model files are downloaded.
How does it tell speakers apart?
It uses the open-source pyannote segmentation model (MIT) plus voice features to group speech by speaker. You can rename or merge speakers afterward.
Is the summary written by AI?
It is extracted with rules (key sentences, keywords, to-dos, decisions). Check important points against the recording.
Which files can I export?
Word (DOCX) meeting notes, Markdown, SRT subtitles and plain text.