Find the moment. Get every word right.
Edit with timestamps, listen while you work, and fine-tune transcripts with precision.
Free
More than a transcript.Your complete recording studio.
Transcription, translation, speaker identification and AI Research privately on your device. For Windows and Linux.
- Local by defaultYour recordings stay on your machine.
- Free transcriptionTranscribe as much as you need.
- Windows + LinuxBuilt for your desktop.
Record meetings.
ProRecord Zoom, Microsoft Teams, Google Meet, Discord, Webex or any other call app on your computer, with no bot joining the call. A live transcript labels you and the other side and is saved as the meeting runs. When you stop, each side is transcribed on its own and TrueScribe writes a summary with the model you choose. Before the first summary it asks which model to use and tells you whether the transcript stays on your computer. On Windows, TrueScribe offers to record when a meeting app starts using your microphone; on Linux, you start recording yourself.
Keep every speaker in the picture.
ProDetect speakers locally with NVIDIA Nemotron 3 on Windows and Linux, give them names and correct who said what. Keep speaker labels consistent throughout the transcript.
Another language. The same recording.
ProTranslate locally and switch between the translation and the original. Keep both available while you review the result.
Compare with the original
Ask more of your transcript.
FreeAsk questions, explore the details and follow up in a conversation. Use a local model or connect a cloud provider of your choice.
From spoken words to finished work.
Free + ProPreview your export before saving. Get text and subtitles for free; Pro adds documents and structured data for the next step in your workflow.
- TXT
- SRT
- WebVTT
- DOCX
- Markdown
- JSON
- CSV
Start with a link.
ProPaste a direct media link or a supported video page, including YouTube and Twitch. Bring the recording into the same editing workflow.
Search every transcript.
FreeKeep your recordings and transcripts together. Search their text to find a passage again, without opening every file.
A whole batch. One workflow.
ProQueue multiple audio and video files for transcription, or point TrueScribe at a folder and it transcribes whatever lands there, even from the system tray. Work through interviews, episodes and recordings without adding each one separately.
Capture a thought while it is fresh.
FreeRecord a voice memo inside TrueScribe, then transcribe and edit it with the same tools you use for imported recordings.
Make your research repeatable.
ProStart with a ready-made prompt for summaries or key points, or save your own. Bring the same questions to your next transcript.
Teach it the names it keeps getting wrong.
FreeEnter names and jargon once and every new transcript is biased toward spelling them right. Add a replacement rule for a term Whisper always mishears, and it is corrected automatically.
Three steps from recording to text
A native desktop app, with no Python, Docker or browser runtime to install. No account, no upload queue, no waiting for a server.
Add your recording
Drop in an audio or video file, or record a dictation directly. With Pro you can also record a meeting or paste a direct media link or a supported public media page.
Transcribe on your machine
TrueScribe runs Whisper locally and picks a model that suits your hardware, downloading it once on first use. It uses AMD, Intel and NVIDIA graphics cards with no CUDA toolkit or driver setup, and integrated graphics and CPU-only machines transcribe on the CPU.
Work with the result
Play back against the waveform, correct the text with undo and redo, name your speakers, translate, and export in the format your work needs.
Transcribe everything
The same workflow fits very different material.
Interviews
Keep two speakers apart, correct names and terms once, and quote from a transcript that carries timestamps.
Meetings
Record the call itself or transcribe a recording you already have. Turn it into text you can skim, search and hand on, without sending the conversation anywhere.
Lectures and talks
Follow the audio next to the text, fix technical vocabulary, and export study notes or subtitles.
Podcasts and video
Produce show notes, subtitle files and searchable archives from the episodes you already have.
Turn any recording into text
Pick the file or source you have and follow the guide.
- MP3 to text: transcribe an MP3 file on your computer
Drop an MP3 into the library and get a transcript on your own computer, with no upload.
- Video to text: transcribe MP4 and other video offline
Transcribe an MP4 or other video file on your computer with nothing to convert, and export text or subtitles.
- Transcribe voice memos from your phone on your computer
Move a voice memo from your phone to your computer and turn it into text you can search.
- Transcribe M4A to text on your own computer
Transcribe an M4A from an iPhone voice memo, a Zoom recording or a handheld recorder, with no conversion.
- WAV to text: transcribe studio and field recordings
Transcribe a WAV export from your DAW, a field recorder or a meeting recording, however large the file.
- Transcribe YouTube video to text on your computer
Paste a YouTube link and get a transcript to correct, search and export, transcribed on your own computer.
- Transcribe podcast episodes to text and show notes
Turn episodes into text, draft show notes from the transcript, export subtitles and search every episode.
Private by default
TrueScribe can run transcription, speaker detection, translation, AI, editing, history and search on your machine. You decide when a feature may use a cloud model or remote endpoint.
Your audio stays on your device
Media files are decoded and transcribed locally. There is no upload step and no processing account.
Models are downloaded once
Whisper and diarization models are fetched on first use and then reused offline.
Cloud processing is an exception
If you choose a cloud model for transcription, translation, AI Research or another feature, the content needed for that operation leaves your device. The local privacy guarantee does not apply to it.
The network is for links and updates
Transcribing a link, downloading a model, checking your licence and error reporting are the times TrueScribe reaches the network.
Buy once, use forever.
Free
Free forever
Core transcription and review without file or time limits.
- Unlimited local-file transcription with every available transcription model
- Dictation recording, history, playback, editing and search
- AI Transcript Research with a local model or an optional configured cloud provider
- Export as TXT, SRT and WebVTT
- Custom vocabulary and automatic replacements for names and jargon
Pro
US$64 one-time
One licence for three devices.
- Local AI translation to 25 languages
- Automatic Speaker detection, naming and assignment
- Watch folders that transcribe new files automatically
- Direct YouTube and Twitch transcription
- Custom one-click prompts for AI Transcript Research
- Batch transcription of many files at once
- Extended export formats
- Meeting recording from any call app, with a live transcript
- Automatic meeting summaries and titles with the model you choose
Questions worth answering first
Does my audio leave my computer?
Local processing keeps your audio and transcripts on your machine. If you choose a cloud model or remote endpoint, the content needed for that operation is sent to that provider. Downloads, media links, licence checks and error reporting also use the network.
Which languages can it transcribe?
TrueScribe uses Whisper models, which cover a wide range of languages. It can detect the spoken language automatically or use the language you select.
Does it use my AMD, Intel or NVIDIA GPU?
Yes. TrueScribe accelerates transcription on AMD, Intel and NVIDIA graphics cards through Vulkan, with no CUDA toolkit to install and no driver setup. Integrated graphics and machines without a graphics card transcribe on the CPU. The suggested model is matched to the machine it runs on, so faster hardware mainly means faster results.
Does it work offline?
Yes, once the models you use have been downloaded. The first transcription needs a connection to fetch the selected model.
Is Pro a subscription?
No. Pro is a one-time purchase.
Which systems are supported?
Windows and Linux, distributed through the Microsoft Store and as an AppImage.
Coming from MacWhisper, Buzz, Vibe, Otter.ai, Descript or Happy Scribe?
TrueScribe runs Whisper locally on Windows and Linux, with no account and no upload. See how it compares: MacWhisper for Windows · Buzz and Vibe alternative · Otter.ai alternative · Descript alternative · Happy Scribe alternative
Start with a recording you already have.
Install TrueScribe, open a file, and read what is in it.