Local, private AI transcription for meetings, dictation, and recordings that runs entirely on your computer
Find who said what and when with your AI agent
Stage
Not given
Startup
Founded
Not given
2025
Based in
GB
SG
Pricing model
Freemium
Freemium
Pricing
$9 USD/month, $89 USD/year (17% discount), or $189 USD one-time lifetime license. All plans include 10-hour free trial with no account or credit card required.
Free: $3 credit included with new accounts; Pay-as-you-go: $1/hour; Starter: $9/mo (unlimited, up to 2 hours per file); Pro: $19/mo (unlimited, up to 5 hours per file); Business: $49/mo (unlimited, up to 10 hours per file). Annual plans include 3 months free.
Key features
On-device audio recording and transcription
Real-time speaker identification with cross-meeting recognition
AI-generated summaries, action points, and chapter markers
Import and transcribe audio and video files locally
System-wide dictation tool with optional LLM cleanup
Calendar integration with Apple Calendar and Google Calendar
Full-text search across all meetings
Export to Markdown, PDF, and via webhooks or MCP
Works fully offline with no internet connection required
Speaker labels and word-level timestamps
52 languages and dialects
Chapters with timestamps
Search and Q&A with citations
Subtitle generation in multiple formats
Integration with ChatGPT, Claude, and AI agents
API and MCP server access
Encrypted storage and privacy controls
Library search across multiple recordings
File upload for meetings, lectures, podcasts and voice notes
What makes it different
No cloud-based servers or analytics; full ownership of your data with lifetime license option
Works completely offline with no account, login, or credit card required for trial
Integrates with your existing tools via MCP, webhooks, and direct API access without data intermediaries
Optional cloud LLM support using your own API keys, giving you control over which provider processes summaries
Word-level timestamps that enable precise subtitle generation for any platform
Ask questions across multiple recordings with citations back to the original moment
Supports use directly within ChatGPT and Claude without leaving your agent
Benchmarked accuracy with 1.5x to 2.3x fewer errors than Whisper large-v3
Permanently searchable library that organizes all transcripts in one place