Audio to text
Audio in.
Text out. No upload.
Drop in a file or share it from any app and ThinkScribe transcribes it on your own device, with speakers told apart and every word synced to the audio. Any length, 28 languages (90+ with the optional Whisper model), no upload.
One purchase covers Mac, iPhone, iPhone Duo, iPad & Apple Watch.
How it works
Three steps, no upload.
- 1
Add the audio
Share a file from Files, Voice Memos, WhatsApp or Telegram, or drag it into the Mac app. MP3, M4A, WAV, FLAC, OGG, WMA and AMR all work.
- 2
It transcribes on your device
Pick the language from the menu of 28. With the optional Whisper model on a Mac, or an iPhone or iPad with 8 GB of memory, the app can also detect it for you.
- 3
Read, search, export
Tap any word to hear that moment. Export TXT, SRT, VTT, JSON, Markdown, PDF, DOCX or CSV, or send a summary to Apple Notes.
Features
Everything a transcription service does, without the service.
Any file, any length
A three-hour recording costs the same as a three-minute one. There is no per-minute meter.
Speaker labels
Voices are told apart automatically and remembered across recordings. Name a speaker once and the name sticks.
28 languages, 90+ with Whisper
A menu of 28 languages on every device. On a Mac, or an iPhone or iPad with 8 GB of memory, the optional Whisper model adds 90+ and detects the language for you.
Word-synced playback
Every word is linked to its timestamp. Click a word to jump the audio there and check it against the recording.
Summaries and answers
Summarize, pull action items or ask a question. The AI answers with citations that jump to the audio.
Eight export formats
TXT, SRT, VTT, JSON, Markdown, PDF, DOCX and CSV, so the transcript fits whatever comes next.
FAQ
Questions, answered.
How do I transcribe an audio file to text on a Mac?
Open ThinkScribe, drag the file in (or use Import), and the transcript appears after a moment. On iPhone, share the file to ThinkScribe from any app. The transcription runs on the device itself, with no upload.
Which audio formats can I import?
MP3, M4A, WAV, FLAC, OGG, WMA and AMR, shared from any app or picked from Files. Voice memos and WhatsApp voice notes work the same way.
Is there a length limit?
No. There's no length limit, and a long recording is processed in the background while you keep using your device.
How accurate is it?
ThinkScribe uses modern speech recognition that runs on your device. Clear audio gives near-verbatim text, and you can switch to another speech model for a recording when one suits the material better.
