AI & Models settings
Settings → AI & Models is where you connect cloud speech and language providers (API keys) and download on-device speech engines. Profiles on the Dictation page choose which provider and model to use; this tab stores credentials and local engines.
What you see
Two sections:
- Providers & API Keys — connect Groq, OpenAI, Anthropic, Google Gemini, OpenRouter, and optional custom endpoints
- Local engines — download, start, stop, or delete SenseVoice Small, Whisper Base, Parakeet TDT 0.6B, and Moonshine Small
Providers & API Keys
If nothing is connected yet: No providers connected yet. Use the dropdown below to add one.
Add or manage a provider
- Under Add provider, choose a service and click Add.
- Paste the API key, optionally Test, then Save.
- Connected providers show a masked key with Replace key and Remove.
| Provider | Typical use |
|---|---|
| Kalam Cloud | Hosted speech and AI on Max (authenticated with your Max license — no separate API key). |
| Groq | Fast cloud STT and LLM (bring your own key). |
| OpenAI | Cloud STT and LLM. |
| Anthropic | Cloud LLM (for polish / language steps). |
| Google Gemini | Cloud LLM. |
| OpenRouter | Cloud LLM; pick models from OpenRouter’s catalog in the profile editor. |
Each provider row notes whether it supports speech (STT), language models (LLM), or both. Many providers include a Get API key ↗ link while editing.
Custom OpenAI-compatible endpoint
| Setting | What it does |
|---|---|
| Custom OpenAI-compatible endpoint | Optional base URL and API key for profiles that use the Custom endpoint provider. Pick the model on each dictation profile. |
| Base URL | OpenAI-compatible root (for example https://api.example.com/v1). |
| API key | Key for that endpoint. |
Local engines
Download and manage on-device speech engines here. Choose which engine a profile uses on Dictation (voice provider → Local).
| Setting | What it does |
|---|---|
| Installed engines | List of local STT models with size, quality, languages, and status |
Local engines
For each engine you can:
- Download (when not installed)
- Start / Stop / Restart when installed
- Delete to remove the model files
| Engine | Best for |
|---|---|
| SenseVoice Small | Default local; multilingual |
| Whisper Base | Broad languages (whisper.cpp) |
| Parakeet TDT 0.6B | High-accuracy English (CC-BY-4.0) |
| Moonshine Small | Fastest local English |
Status badges include states such as Running, Stopped, Starting, and Error. When running, approximate RAM use may appear. Hardware warnings appear if your machine cannot run a model, or if the engine is not available on this platform.
If a local speech engine runtime is installed, you may also see Uninstall engine.
With Sensitive app detection on, matching apps force on-device STT. If no local engine is installed and running, dictation fails instead of sending audio to the cloud. See Privacy settings and Local models.
Plan gates
| Feature | Free / Pro | Max |
|---|---|---|
| BYOK providers (Groq, OpenAI, …) | Yes (your keys) | Yes |
| Custom OpenAI-compatible endpoint | Yes | Yes |
| Local engines | Yes | Yes |
| Kalam Cloud hosted STT / AI | No | Yes (included in Max) |