Skip to content
speakr
Productivity & Wikis
Self‑hosted AI transcription and intelligent note‑taking platform that keeps your conversations private
Python
·
Latest v0.10.2-alpha · 11d ago
Security brief →
Features
-
Flexible audio capture from microphone, system or tab audio, drag‑and‑drop files, and auto‑import folder
-
Bring‑your‑own ASR with WhisperX, OpenAI, Mistral/Voxtral, AssemblyAI, plus speaker diarization and voice profiles
-
Automatic summaries, event extraction, per‑recording chat, and full‑library semantic search
-
Multi‑user collaboration with OIDC SSO, groups, granular sharing permissions, and public links
-
REST API v1 (Swagger), signed webhooks, usage budgets for LLM tokens and transcription minutes
Config change
v0.10.2-alpha
Breaking risk
·
Auth
Email verification enforcement + speaker labeling
Upgrade now
v0.10.1-alpha
Breaking risk
·
Auth
Security hardening and access control improvements
Review required
v0.10.0-alpha
Breaking risk
·
Auth
JSON 401 + Incognito hardening + Upload fix
No immediate action
v0.9.7-alpha
Breaking risk
·
MP3 playback + transcript clickability + retention sweep
No immediate action
v0.9.6-alpha
New feature
·
Merge recordings + Markdown export
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
About
Languages
Python
·
HTML
·
JavaScript
Search tools, categories, lists, and users
Use ↑↓ to navigate, Enter to open, Esc to close
No results for ""
⌘K to open
↑↓ navigate
⏎ open
