Most transcription services bill by the minute or sell a Pro tier for batch work. templobe runs English speech models on your own Mac instead: no per-minute credits, no subscription, and your audio never leaves the machine. Transcription is free for beta users, permanently.
No card. No per-minute fees. mp3, wav, m4a. macOS 13+. Apple silicon.
| What matters | templobe | Typical cloud service |
|---|---|---|
| Cost | Free for beta users, permanently | Per-minute credits or a monthly subscription |
| Batch work | Included in the free beta | Often locked behind a Pro tier |
| Card required | No | Usually yes, even on a free trial |
| Where audio goes | Stays on your Mac | Uploaded to a server |
| Works offline | Yes, after one sign-in | No |
| Account | One activation account; never sees audio | Cloud account holds your recordings |
| Export | txt, md, srt, vtt | Varies by provider |
| Data retention | You delete local files; no copy elsewhere | Depends on provider policy |
Cloud services differ widely; this compares the common model, not one specific vendor. Check each provider's pricing and data policy before sending confidential audio.
On first run templobe downloads an English speech model onto your Mac. That is the only download — after it, transcription runs offline.
Choose mp3, wav or m4a files. A single batch holds up to 50 files, 2GB each and 5GB total. Nothing is uploaded.
Review each transcript against playback in the local library, then export as txt, md, srt or vtt. No credits consumed.
Yes. Transcription is free for beta users, permanently. There are no per-minute credits and no card required to reserve the beta. Future paid features will be optional add-ons such as summaries, translation and vocabulary packs — core transcription is not going behind a paywall.
Because the work happens on your Mac using local models, not on rented servers. Servers are what cloud services meter. Your hardware does the transcription, so there is no per-minute cost to pass on during the beta.
Up to 50 files per batch, 2GB per file and 5GB per batch. You can run as many batches as you need during the beta.
You sign in once to activate the app and download the model. The activation account never receives your audio — transcription stays on the machine.
No. Speech recognition runs on your Mac with local models. There is no upload step.
Yes, after the first sign-in and model download. Airplane mode is a supported state.
mp3, wav and m4a. Video files are not supported in this beta.
Yes — transcription is speech-to-text. You import an audio file and get text back, exported as txt, md, srt or vtt. It is not live dictation: nothing listens to your microphone, and there is no real-time transcript.
It is a beta: English audio only, no speaker labels, no direct video import. The tradeoff is that the app ships earlier and beta users keep free transcription for good.
Beta users get free transcription for good. Leave your email to reserve the beta — no payment, no card. We'll send the signed build to the same inbox once it's ready. No newsletter, no drip sequence, no sharing your address.
We sent a confirmation link. Click it to confirm your address — your reservation is complete, and the beta build goes to the same inbox the moment it's signed.