MacWhisper batch transcription: a folder of recordings in one run, and how to make it faster
By Ryleigh Newman · Published
MacWhisper's Batch Transcription takes many files at once, which its help center pitches for a backlog of tens of interviews transcribed overnight at the highest quality. You can export each file in several formats in the same run. This page covers starting a batch, the export options, what changes when you use a cloud provider, and the settings MacWhisper's own help center gives for speed.
I built YapToText, a different dictation app for the Mac, so read what I say about MacWhisper with that in mind. Every fact about MacWhisper here comes from its own help center, read on October 10, 2026.
This app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.
This guide in other languages: Čeština, Deutsch, Español, Français, Magyar, Bahasa Indonesia, Italiano, 日本語, 한국어, Nederlands, Polski, Português, Русский, ไทย, Türkçe, Tiếng Việt, 简体中文, 繁體中文
Starting a batch
- From the home screen. Click the Batch Transcription button.
- From Open File. Choose several files at once.
- By dragging. Drop several files onto MacWhisper together and the Batch window opens.
Links to online media do not work in a batch yet. The YouTube transcription page covers those one at a time, and watch folders transcribe new files as they arrive without a batch at all.
Export formats
In the top right of the Batch window, Add Format adds another export format. You can add as many as you want, including the same format twice with different options, so one run gives every file in each format you picked. The bottom left shows the total length of all the audio, which gives an idea of how long the batch will take.
Using a cloud provider
From MacWhisper's help article Cloud Transcription, read October 10, 2026. The help center adds that 1 GB uploads may fail on a slow connection.
| Provider | File size limit |
|---|---|
| Groq | 25 MB |
| ElevenLabs | 1 GB |
| Deepgram | 1 GB |
| One more AI provider, and compatible custom providers | 25 MB for that provider |
Add your own API key in Settings, Cloud Transcription, then pick the provider in the model picker at the top right of the home screen. A cloud provider receives your audio, so it is a privacy choice as well as a speed one. The MacWhisper privacy page goes into it.
Making it faster
From MacWhisper's help articles Transcription Is Slower Than Expected and Switching to a WhisperKit model, read October 10, 2026.
| Mac | What the help center suggests |
|---|---|
| Intel | On-device transcription is much slower without machine learning hardware. A cloud provider is faster. WhisperKit models do not run on Intel |
| Any M-series | If MacWhisper crashed once it may be in a compatibility mode, common on M1. In Settings, Advanced, WhisperKit, make sure Disable all GPU usage is off |
| Pro, Max or Ultra chips | On the same screen, turn on VAD, set Concurrent Workers to 64 and Text Decoder to GPU |
The help center also recommends WhisperKit models, found under Manage Models with the WhisperKit filter, as faster and better with silence or music in long files. It names the Turbo model as a good choice for many Macs. The first load of a large model can take a few minutes, and later loads are fast.
Files in YapToText
MacWhisper from its help center, read October 10, 2026. YapToText from its own settings.
| MacWhisper | YapToText | |
|---|---|---|
| Several files at once | Batch Transcription | Drop or choose a file |
| Export formats | Several per run | Plain text, with Copy, Insert and Send |
| Cloud providers | Optional, with your own API key | None, it runs on the Mac |
| Formats it reads | Audio and video files | Anything macOS can decode, including Voice Memos |
For a backlog of interviews in several formats, MacWhisper's batch is the better tool, and I would say so. YapToText is for dictation, with file transcription as a plain text extra. The interview transcription guide compares the options.
This app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.
The short version
- Start. Drop several files onto MacWhisper.
- Formats. Add Format, as many as you need.
- Time. The total audio length shows in the bottom left.
- Cloud limits. 25 MB for some providers, 1 GB for ElevenLabs and Deepgram.
- Speed. WhisperKit models, GPU on, and on big chips 64 workers.
If MacWhisper changes Batch Transcription, open an issue on GitHub and I will update this page. Every one gets read.
This app is completely free. You don't have to make an account. There are no subscriptions, no difficult downloads, and nothing is locked. Made for Apple silicon Macs. Source on GitHub.
Related
Sources
- https://docs.macwhisper.com/article/19-batch-transcription (checked 2026-10-10)
- https://docs.macwhisper.com/article/18-cloud-transcription (checked 2026-10-10)
- https://docs.macwhisper.com/article/34-transcription-is-slower-than-expected (checked 2026-10-10)
- https://docs.macwhisper.com/article/29-switching-to-a-whisperkit-model (checked 2026-10-10)
- https://github.com/ryleighnewman/YapToText (checked 2026-10-10)
- https://apps.apple.com/us/app/yaptotext/id6786382289 (checked 2026-10-10)
Questions
Can MacWhisper transcribe multiple files at once?
Yes. Drag several files onto it, choose several in Open File, or use the Batch Transcription button on the home screen.
Can MacWhisper export several formats in one batch?
Yes. In the Batch window, Add Format adds as many export formats as you want.
Why is MacWhisper so slow?
On Intel Macs on-device transcription is slow, so a cloud provider helps. On M-series Macs check that Disable all GPU usage is off in Settings, Advanced, WhisperKit.
What is the file size limit for MacWhisper cloud transcription?
It depends on the provider: 25 MB for Groq, up to 1 GB for ElevenLabs and Deepgram.
Does YapToText do batch transcription?
It has no batch window. You drop or choose a file and get plain text, transcribed on the Mac.