Turn any document into a two-voice podcast you can listen to on your commute
Open source dictation for Mac with local AI, instant speed and complete privacy
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
RO
Pricing model
Freemium
Paid
Pricing
Free: 3-minute preview of any episode with spoken-intro watermark, no download. Pro: $12/mo for unlimited episodes up to 50,000 characters, MP3 downloads, no watermark, priority queue. Credit pack: $9 for 20 full episodes up to 50,000 characters with MP3 downloads, credits never expire, no subscript
One Mac: $15 (or $9 for first 10 buyers); Three Macs: $20; Team (10 Macs): $79. 3-day free trial with everything unlocked. Free updates. 14-day refunds.
Key features
Paste text, PDF, DOCX upload, or article URL input
Two-host conversational format with Q&A dialogue
Self-hosted speech synthesis models
5–15 minute episodes with chapters and synced transcript
MP3 download capability on Pro plan
Free 3-minute preview on any document
Priority queue processing for Pro subscribers
Support for documents up to 50,000 characters
No watermark on Pro and Credit pack episodes
Dictation into any app with one keyboard shortcut
Local speech processing in about 200 milliseconds
Automatic clean speech with filler word removal
Learn corrections to improve accuracy per user
21 vocabulary packs for specialized fields
Custom vocabulary packs from CSV or JSON files
Notes with searchable history and time-based reminders
Meeting mode with speaker labels and timestamps
Supports 25 European languages
Runs completely offline with no account required
What makes it different
Two-voice dialogue format keeps listeners engaged better than monotone reading
Self-hosted voice models optimized specifically for natural Chinese and Japanese pronunciation
No per-character pricing, so long documents are voiced end-to-end without truncation
Automatically rewrites source documents into conversational format
Credit packs never expire, providing flexible usage without subscription commitment
Open source GPL-3 code on GitHub you can read, build and verify
Complete privacy with no server, no account, no audio sent anywhere
Fastest local transcription at about 200 milliseconds latency
One-time purchase with free updates and no subscription
Works in terminal, code editors and AI coding agents
DuoCast
Zumbo