Speech engines: On-device vs Cloud
You choose where speech recognition runs—on your computer or in the cloud, whichever you like. Kalam treats both as equal options and sets no forced default. Set your shared baseline engine under Dictation → Models, and override individual profiles whenever a job calls for something different.
On-device vs Cloud comparison
| Consideration | On-device models | Cloud providers (your own API keys) |
|---|---|---|
| Where audio is processed | Entirely on your computer | Sent to your chosen cloud provider |
| Works offline | Yes—after downloading the model once | No—requires an active internet connection |
| Setup needed | Download a model (103–460 MB) under AI & Models → Local providers | Paste an API key under AI & Models → Cloud providers |
| Password managers & Sensitive apps | Runs seamlessly without interruption | Automatically switched to an on-device model (fails closed if none installed) |
| Plans | Included on Free and Pro | Included on Free and Pro |
If you dictate inside a password manager or private window while Sensitive apps protection is active, Kalam blocks cloud audio automatically. Having an on-device model downloaded prevents failed takes in sensitive windows.
Available engines
On-device engines
Download and run models locally through Settings → AI & Models → Local providers:
| Runtime | Model | Download size | Languages | Guide |
|---|---|---|---|---|
| Sherpa-ONNX | SenseVoice Small | 150 MB | English, Chinese, Japanese, Korean, Cantonese | Local models |
| Whisper.cpp | Whisper Base | 142 MB | 99 languages | Local models |
| Sherpa-ONNX | Parakeet TDT 0.6B | 460 MB | English | Local models |
| Sherpa-ONNX | Moonshine Small | 103 MB | English | Local models |
Cloud speech providers
Connect your own API keys in Settings → AI & Models → Cloud providers:
- Groq (speech + AI polish)
- OpenAI (speech + AI polish)
- Google AI Studio (speech + AI polish)
- Deepgram (speech)
- AssemblyAI (speech)
- ElevenLabs (speech)
- xAI (speech)
Max (hosted service)
Max is listed in the app and on kalamvoice.com/pricing, and is not for sale yet. When available, Max will provide managed speech and AI so there are no local downloads or external keys to manage.
Assign an engine
- Connect a Cloud provider key or download a Local model under Settings → AI & Models.
- Open Dictation → Models to choose the shared speech engine used by Plain dictation and inheriting profiles.
- To give a specific profile (such as Coding or Notes) its own engine, open that profile in Dictation and change Hear your voice.