Runs entirely on your Mac
Open Source

Your audio and video, distilled.

Record meetings or bring in podcasts, lectures, videos, and YouTube talks. Turn them into searchable knowledge — locally, in minutes.

Your machine. Your models. Your knowledge base.

$ brew install --cask audistill/tap/audistill
Audistill app showing podcast episode brief with AI-powered search and transcript analysis
The Pipeline

Three steps. Zero friction.

From raw audio or video to searchable knowledge — entirely on your machine.

01

Drop it in

Audio files, video files, YouTube links, RSS feeds, or any media URL. One input field auto-detects everything.

MP3MP4MOVYouTubeRSSURL

YouTube import is powered by yt-dlp, a third-party open source project.

Input
Drop files or paste a link
On-Device
1 hr audio/video< 2 min

30–50× realtime on Apple Silicon

Summarized via OpenRouter — 200+ models
02

Distill it

Transcribed on-device in minutes using Parakeet TDT on Apple Silicon. Then summarized, structured, and tagged by any model you choose via OpenRouter.

Media files never leave your machine.

03

Work with it

Search across everything. Ask questions. Surface patterns. Generate new content from your knowledge base.

Output
SearchFull-text across all transcripts
ChatAsk questions about your media
CreateGenerate from your knowledge

What you get

Every tier. Every feature. No upsells.

Ask, Search, Create

A research assistant with tools. Search across your library, extract patterns, and generate new content — not just a chatbot.

Find every mention of churn across last month's interviews

3 matches found

Ep. 12 — 04:32
Ep. 8 — 11:15
Ep. 3 — 22:48

Audio + video ingest

Import audio, video, YouTube links, RSS feeds, and direct media URLs. One field, auto-detected.

Record meetings directly

Capture Mac audio, one microphone, or both. Pause when needed — recording continues while Audistill is hidden or you view another Episode.

On-device transcription

30-50x realtime on Apple Silicon. For video files, Audistill extracts the audio track with FFmpeg and transcribes it locally.

Powered by OpenRouter

Access 200+ models via OpenRouter. Bring your own API key — no markup, no middleman.

Custom templates

Define how content gets shaped. We call them Recipes — run on any transcript.

Full-text & web search

Find anything across every transcript locally, or let the AI search the web to enrich your results.

Use Cases

See yourself in here

Same app. Different workflows. Same result: knowledge you can actually find again.

Developer

12 conference talks.
One search bar.

Paste YouTube links from WWDC, JSConf, Strange Loop — or import the video files directly. Build a searchable library of every talk you watched.

React Server Components8 results
Dan Abramov — RemixConf '2414:32

…RSC eliminates the waterfall by moving data fetching to the server…

Ryan Florence — React Summit08:15

…server components change how we think about the component tree…

Kent C. Dodds — Epic Web22:48

…the mental model shift with RSC is fundamentally about ownership…

↑ found across 6 months of talks

Record during a meeting

Record the meeting.
Keep every decision.

Capture Mac audio and your microphone directly in Audistill. Stop when you're done, and get a Recorded Episode with an on-device Transcript — ready for decisions and action items.

Action Items — Q3 Planning3 items
Finalize API spec by Friday
Sarah
Set up staging environment
Marcus
Review pricing proposal
You
Research

30 episodes. One question.

Subscribe to feeds. Auto-ingest. Search across months of listening.

Startup Pods30 ep
pricing strategy
Ep. 12 — Why PLG pricing fails
Ep. 8 — Unit economics deep-dive
Ep. 3 — Pricing page teardown
7 results
Pattern Analysis — 15 interviews
Onboarding confusion11/15
Pricing unclear8/15
Missing integrations6/15
Performance issues4/15
“What pain points keep coming up?”
Product

Customer interviews →
patterns in minutes.

Ingest 15 customer calls. Ask one question across all of them. See what actually keeps coming up — not what you assumed.

Learning

One lecture. Five outputs.

Run different Recipes on the same 90-minute recording. Brief for review, detailed for study, key quotes for your paper.

The lecture introduces three competing models of attention allocation in cognitive load theory, with emphasis on the redundancy effect.

Key distinction: intrinsic vs. extraneous load — the speaker argues most instructional design failures are extraneous.

Actionable takeaway: chunk information into 3–5 segments before testing recall.

Generated in 8s · Cognitive Psych 301 · Lecture 7Claude 3.5 Sonnet
Pricing

One-time purchase

Every tier includes all features. Forever.The only difference is how many Macs you own.

Solo

One Mac, full power.

$25once

1 Mac · Lifetime license

Get Solo
Most popular

Personal

Laptop + desktop.

$39once

2 Macs · Lifetime license

Get Personal

Extended

All your machines.

$49once

3 Macs · Lifetime license

Get Extended
All features includedLifetime updatesNo subscriptionBYOK via OpenRouter14-day free trial

Questions

Are my audio or video files sent to the cloud?

No. Transcription runs entirely on your Mac using Apple Silicon. Media files never leave your machine. AI features (summaries, chat, web search) use your OpenRouter API key — calls go directly from your Mac to the model you choose.

Can I record meetings directly in Audistill?

Yes. Choose Add → Record audio or press Command–Shift–R. Capture Mac System Audio, one selected built-in, Bluetooth, or USB microphone, or both. You can pause, hide or minimize Audistill, and view another Episode without stopping the session. Stop and process creates a Recorded Episode through the usual on-device Transcription and Ingest flow. The recording audio is temporary — it is deleted after the Transcript is stored, so Audistill is not a permanent playback library. macOS requests Screen Recording access for System Audio and Microphone access for your microphone.

Which files and URLs can I import?

Audistill supports audio files like .mp3, .m4a, .wav, .flac, .aac, .ogg, and .opus, plus video files like .mp4, .mov, .mkv, and .webm for transcription. Video is used as an audio source only — no video playback or visual analysis. You can also import YouTube links and direct media URLs. If a video has no audio track, Audistill will tell you.

“Your media files never leave your machine. Transcription happens entirely on-device.”

What does 'bring your own model' mean?

Audistill connects to LLMs via OpenRouter. You provide your own OpenRouter API key and pick from 200+ models for summaries and chat. Typical cost: a few cents per episode. We never see your key or your data.

What search capabilities are included?

Audistill includes full-text search across all your transcripts and generated documents. The AI assistant can also perform web-based search to enrich answers with up-to-date information from the internet.

What happens after the 14-day trial?

The app remains viewable — you can browse your library, read transcripts, and search. Ingest, chat, and recipe execution require a license to continue.

Is this a subscription?

No. One-time purchase, lifetime updates. Pick the tier that matches how many Macs you own.

What Mac do I need?

Any Mac with Apple Silicon (M1 or later). macOS 13 Ventura or newer. Intel Macs are not supported.

Can I build from source instead of buying?

The source code is available. You can build and run it yourself. The paid download gives you a signed, notarized binary with auto-updates and supports continued development.

Open Source

Built in the open

Audistill is fully open source. Inspect, modify, contribute —your tool, your rules.

audistill/audistill

Main repository

AGPL-3.0
Contribution Activitylast 13 weeks
Stars
Forks
Issues
PRs

Why open source?

Verify privacy claimsInspect every line. Confirm nothing phones home.
Customize freelyAdd integrations, tweak recipes, shape it to your workflow.
Build from sourceDon't trust binaries? Compile it yourself.
Contribute backFix a bug, add a feature, improve docs — PRs welcome.
Star on GitHub
$ git clone https://github.com/audistill/audistill.git
Free to build & run yourself. The paid download supports development and gives you auto-updates + a signed binary.
Get Started

Take it from here.

14 days free. No credit card. Pick your path.

Recommended

Download

Signed & notarized .dmg

One-click install. Auto-updates. Supports development.

Download for Mac
Notarized by Apple

Homebrew

For terminal lovers

Install and update via Homebrew Cask. Same signed binary.

$ brew install --cask audistill/tap/audistill
$brew upgrade to update

Build from Source

Full control

Clone, inspect, build. Free forever. No telemetry, no limits.

View on GitHub
AGPL-3.0 License
System Requirements
Apple SiliconM1 or later
macOS13 Ventura+
Storage~200 MB