NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #4814 most downloaded on PyPI
Official pyannoteAI Python SDK
Last release 8 months ago
14 Jan 2026
Ships fairly regularly
a new release about every 3 months
Most releases are documented
notes for 6 of 7 stable releases
Nothing withdrawn
no release was ever pulled
2 years old
7 releases · first in 2025
One column per month.
feat: add support for STT orchestration
feat: add support for passing audio as a {"audio": str | Path} mapping
{"audio": str | Path} mapping{"waveform": np.ndarray | torch.tensor, "sample_rate": int} mappingNothing published for this version
fix: fix "missing token" error message
Add support for Precision-2 model
Precision-2 modelAllow arbitrary kwargs in diarize, identify and voiceprint
diarize, identify and voiceprint- *Hello world!*
Your coding agent can read these notes before it upgrades. Set up the MCP server →