audapolis: an editor for spoken-word media
Don’t want to install audapolis? Drop the file here.
The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.
A word-processor-style editor for podcasts, interviews and radio: it transcribes the recording locally, then you cut the media by cutting words. No cloud at all.
Get audapolis Official site & pricing
audapolis is a free, offline text-based editor for spoken audio and video: it transcribes with Vosk, then you edit the media by editing the words. The open-source answer to Descript-style editing.
If you need the transcript itself (accurate text, timestamps, an SRT, a summary) rather than an edit, a hosted transcriber is the faster route.
What it is
audapolis is an AGPL-3.0 desktop editor for spoken-word media from the bugbakery collective. It transcribes audio or video automatically, then gives you a word-processor-like view where deleting or moving words edits the underlying media, for podcasts, audiobooks, interviews or radio. Transcription runs locally through Vosk models in its bundled server, and no data goes to a cloud. Builds exist for Windows, macOS (Intel and Apple Silicon) and Linux (AppImage, deb, rpm, pacman). It was funded from September 2021 to February 2022 by Germany's Federal Ministry of Education and Research through the Prototype Fund. The latest release, v0.3.1, shipped on 26 November 2025.
Watch out for: Slow release pace: v0.3.1 (26 November 2025) followed a long gap and removed punctuation reconstruction. Transcription uses Vosk models, which trail current Whisper-class models on accuracy.
When you need the transcript, not the edit
- Drop the audio or video file into the box at the top of this page, or paste a link (YouTube, a podcast or RSS feed, Google Drive, Twitch or Kick). Nothing to install and no GPU needed.
- The language is detected automatically and the transcript stays in the language that was spoken (WhipScribe does not translate).
- You get punctuated text with timestamps, a summary with chapters, and subtitle files.
- Read the summary free. A pack from $6 (500 minutes) opens the full transcript and the downloads: TXT, DOCX, SRT, VTT and JSON. Packs are one-time purchases and credits never expire.
- Files can be up to 10 hours or 5 GB per file.
Related: SRT generator · Transcribe a podcast · Descript · Vosk · Pricing
Install / use
Go to audapolis github.comKey specs
What people actually do with audapolis-style transcription
The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.
Wire it into ZapierMake.comAmazon S3SlackGoogle DriveEmergent
Features
| Speaker diarization | Not stated |
| Word-level timestamps | Not stated |
| Streaming / real-time | Not stated |
| Languages supported | — |
| HIPAA eligible | No |
Links
- github.com/bugbakery/audapolis ↗AGPL-3.0 · TypeScript + Python server · v0.3.1 on 2025-11-26
- audapolis releases ↗Windows, macOS and Linux builds
audapolis vs Whipscribe
| Feature | audapolis | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | $6–$24 one-time packs (credits never expire) · first 20 minutes free |
| Speaker identification | No | Named in the summary, key quotes and chapters |
| Word timestamps | No | Yes |
| Streaming | No | No |
| Languages | — | 99 |
| Platforms | Windows, macOS, Linux | Web, API, MCP |
Alternatives to audapolis
Frequently asked about audapolis
Is audapolis still maintained?
Slowly. v0.3.1 was released on 26 November 2025 after a long gap, mainly as a stable base, and the repository had commits in 2026. Expect occasional releases rather than a steady cadence.
Which speech engine does audapolis use?
Vosk models, run locally by its bundled server. v0.3.1 added more language models and removed punctuation reconstruction because it did not work in many cases.
Is audapolis like Descript?
In approach, yes: you edit audio and video by editing a transcript. It is free, open source and fully offline, with fewer features.
Which platforms does audapolis run on?
Windows (x64), macOS (Intel and Apple Silicon) and Linux (AppImage, deb, rpm and pacman packages).
What is audapolis?
audapolis is a free, offline text-based editor for spoken audio and video: it transcribes with Vosk, then you edit the media by editing the words. The open-source answer to Descript-style editing.
Is audapolis free?
Yes. audapolis is free and open source.
How do I install audapolis?
Download the installer for your platform from https://github.com/bugbakery/audapolis/releases/latest. No terminal needed.
Is audapolis HIPAA compliant?
audapolis does not claim HIPAA compliance. For PHI, run it on infrastructure you control or choose a service that will sign a BAA.
What are the limitations of audapolis?
Slow release pace: v0.3.1 (26 November 2025) followed a long gap and removed punctuation reconstruction. Transcription uses Vosk models, which trail current Whisper-class models on accuracy.
Who is audapolis best for?
Podcasters and radio makers who want text-based editing like Descript, free and offline.
What should I know before choosing audapolis?
If you need the transcript itself (accurate text, timestamps, an SRT, a summary) rather than an edit, a hosted transcriber is the faster route.
Does audapolis run offline?
audapolis runs on your own machine — it is open source, so nothing leaves the computer unless you configure it to.
Can I use audapolis in the browser?
No — audapolis is a Windows, macOS and Linux application, not a web app. You install it rather than sign in to it.
What kind of tool is audapolis?
In this directory audapolis is filed under editor, desktop app as a open-source tool.
Can I automate audapolis-style transcription without running it myself?
Yes. If what you want is transcripts rather than the tool itself, Whipscribe does the same job as a hosted API: submit a file or URL, poll a job id, pull the result as txt, json, srt, vtt or docx. $0.012 a minute — about $0.72 an audio hour — bought as credits that never expire. The automation recipes on this site show it wired to Drive folders, Zoom recordings, S3 buckets and no-code platforms.
Whipscribe is a hosted transcription service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.
Transcribe your recordings
Running audapolis yourself? Send the same file here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step
Explore
All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing
Long recording to get through?
One file up to 10 hours, as an upload or a link: see MP3 to text for long recordings, transcribing a podcast episode and the SRT file generator.
Comparing tools before you pay?
If you would rather pay a service than run software yourself: see an honest roundup of the best transcription services, affordable transcription priced per hour and our transcription service with prices and turnaround.