AI speech to text workspace for converting audio, video, and live recordings into searchable, editable transcripts
Make viral Outstanding Tiny Desk AI videos from 1–5 photos
Stage
Not given
Startup
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Paid
Pricing
Not given
Solo: $7.99 for 1 video. Trio: $17.99 for 3 videos ($6.00 per video). Full Band: $26.99 for 5 videos ($5.40 per video). One-time payments with no subscription. All videos are 720p HD, 15 seconds, vertical 9:16, include MP4 with song, MP4 without music, and GIF, with no watermark. Failed generations
Key features
Media URL import to transcribe online content
Support for 100+ languages with automatic detection
Speaker labels to identify multiple speakers
Searchable and editable transcript editor
Export to TXT, SRT, DOCX, and JSON formats
AI Summary and Analytics tools (Pro and Max plans)
Transcript translation into 100+ languages (Pro and Max)
Email delivery of transcripts and summaries (Pro and Max)
Upload 1–5 photos and AI fills empty band roles
720p HD vertical 9:16 MP4 videos, 15 seconds long
MP4 with song, MP4 without music, and silent GIF included
No sign-up required to generate videos
3–5 minute generation time
Video quality review and re-generation policy
No watermark on videos
What makes it different
Browser-based with no installation required and no account needed to start
Built on OpenAI Whisper for better handling of accents, background noise, and multiple languages
Fast transcription in roughly the time it takes to brew a coffee
Accessible by default with full keyboard control and screen-reader compatibility
Uses Seedance 2.0 video model to re-film the actual moment with your photos, not static face-swapping
Based on viral trend from October 2026 with massive social media momentum
Pay once per video with no subscription or recurring charges
Same price whether video uses 1 or 5 people from photos
Original audio from Charlie Wilson's June 2023 NPR performance included
Speech Text
Tiny Desk AI