Transcription can run on your machine or in the cloud. The trade-off is the obvious one — privacy and offline capability against accuracy and speed on modest hardware.
On-device models
These are Whisper builds, downloaded on demand and stored locally. Six are offered:
| Model | Size | Notes |
|---|---|---|
| Small | 466 MB | The only model available on the free plan; usable on CPU |
| Large V3 Turbo | 1.62 GB | Recommended — near-Large accuracy, much faster |
| Large V3 Turbo Q5 | 574 MB | Quantised, smallest of the Turbo family |
| Large V3 Turbo Q8 | 874 MB | Quantised, balanced |
| Medium | 1.53 GB | Superseded by Turbo for most uses |
| Large V3 | 3.09 GB | Most accurate, slowest |
GPU acceleration
GPU use is on by default where it is supported. What that means depends on your platform:
| Platform | Acceleration | Setup |
|---|---|---|
| macOS (Apple Silicon) | Metal, roughly 7× faster than CPU | Nothing to do |
| Windows (NVIDIA) | CUDA, dramatically faster | A GPU runtime is downloaded on request from the On-Device Models page |
| Windows (other) · Linux | CPU | The toggle is disabled when no capable device is found |
On macOS you can additionally download a Neural Engine encoder for a model from the same page. It is never installed automatically, and if it fails to load, transcription silently continues on Metal.
Cloud models
Cloud transcription is more accurate on accented speech, noisy rooms and technical vocabulary, and it does not care how fast your machine is. Signing in gives you a built-in provider with no key setup — see Using the built-in provider.
Mixing the two
You do not have to choose once. Each workspace can override the speech model, so a workspace for confidential notes can pin an on-device model while everything else uses the cloud. Set it on the workspace, not globally.
What happens when the cloud fails
On a network error or timeout, InkSpoke falls back to a local model and finishes the job. Two exceptions are worth knowing:
- Quota, billing and authentication errors do not fall back — retrying locally would hide a problem you need to fix.
- On the free plan there is no local fallback, because on-device models beyond Small are not part of that plan. The recording is preserved instead and offered with a Retry action, so your words are not lost.