The offline video editor built for podcasters and long-form creators. Works on hour+ files without slowing down. No subscription. No data leaves your machine.
Transcription, speaker labels, AI editing, noise reduction, and more — all offline, one-time price.
Delete words to cut, mute, adjust gain, or change speed — all by editing text. Full keyboard shortcuts with custom remapping. Edit like a doc.
Virtualized transcript and chunked waveform — no lag on long recordings. Speaker diarization labels who said what.
Filler word removal, silence trimming, and clip suggestions for social media. Works with local Ollama or cloud OpenAI/Claude.
100% offline. No account, no cloud, no telemetry. Save and load projects (.aive) with auto-save crash recovery.
$49 Pro, $99 Business. Pro users upgrade to Business for $50. Own it forever.
MP4, MOV, WebM, or WAV. Captions, chapters, noise reduction, background removal, Ken Burns zoom, and music with auto-ducking. Fast stream-copy mode in seconds.
MP4, MOV, MKV, WebM, M4A. Transcription starts automatically with your choice of Whisper model.
Select words → cut, mute, speed up, or adjust gain. Drag zones on the waveform. 100-level undo/redo.
Choose your format, resolution, captions, and loudness target. One click to export.
Start free. No credit card required. Upgrade when you're ready.
$0
7 days, core features
$49
One-time payment
$99
One-time payment
Pro users upgrade for $50
Beta v0.1.0 — Linux (x86_64). Windows coming soon.
Linux (.deb • .rpm • .pkg.tar.zst • AppImage)
Yes. Transcription, AI features, and export all run locally. No data ever leaves your machine. No account required. The only time it touches the network is downloading Whisper models (optional) or if you connect to a local Ollama instance.
TalkEdit handles hour+ files without issue. The transcript uses virtualized rendering and the waveform uses chunked loading — no lag, no crashes. We regularly test with 2-3 hour podcast recordings.
30-day money-back guarantee, no questions asked. If TalkEdit doesn't work for you, email us and you'll get a full refund.
Input: MP4, MKV, MOV, AVI, WebM, M4A. Export: MP4 (H.264/H.265), MOV, WebM, WAV. Captions: SRT, VTT, ASS. Resolutions from 720p to 4K.
Yes. Beta is Linux-first, but the app is built with Tauri which supports all three platforms. Windows and macOS builds will follow based on beta demand.
No. Transcription works on CPU (slower but usable). GPU (CUDA) speeds it up significantly. AI features use lightweight models that run on any modern machine with 8GB+ RAM.