Local, Ollama, and cloud enhancement providers
Choose and configure where optional transcript cleanup runs.
Choose where cleanup runs
AI Enhancement optionally cleans a completed dictation before Whisperstream inserts it. Choose Local to run cleanup on this PC, or configure Ollama, Gemini, OpenAI, Anthropic, or a Custom service. Enhancement is off by default.
| Provider | Where cleanup runs | What you configure |
|---|---|---|
| Local | On this PC | Gemma 4 E2B download and speed check |
| Ollama | Where the selected Ollama model runs: this PC, another computer, or Ollama Cloud | Endpoint and exact Model name |
| Gemini | Google Gemini | API key and Model |
| OpenAI | OpenAI | API key and Model |
| Anthropic | Anthropic | API key and Model |
| Custom | The OpenAI-compatible service at your Base URL | Base URL, Model, and API key |
Enable AI Enhancement
- Open Enhancement.
- Select a Provider.
- Review any provider notices that appear. Continue only if you want to use that provider.
- Complete the fields or guided Local setup shown for the provider.
- Turn on AI Enhancement if it is still off.
For a configured service, wait for the status to show Connected. Local setup is complete when its download and speed check finish successfully. If setup fails, expand the connection card and follow the message shown.
The provider controls where cleanup runs. To choose how text is rewritten, see Profiles and routing.
Set up Local enhancement
Choose Local when cleanup must remain on this PC. Whisperstream's Local provider uses Gemma 4 E2B and does not need an API key.
- Select Local under Provider.
- If the Local setup guide opens, choose Continue to download the model and run the speed check.
- Follow the result shown to finish setup.
- Turn on AI Enhancement if it is still off.
After setup, cleanup runs on this PC. The speed check helps confirm that the model is suitable for the computer.
Set up Gemini
Gemini is the recommended quick setup for a bring-your-own-key cloud provider.
- Open Google's Gemini API key guide and sign in to Google AI Studio.
- Create or select a Google Cloud project if prompted.
- Create an API key and copy it. Follow Google's current restriction guidance on the same page.
- In Whisperstream, select Gemini and paste the key into API key.
- Keep the recommended Model or choose another available to your key, then complete the standard enablement steps above.
Google may offer a free tier for eligible accounts and models. Regional availability, limits, data terms, and pricing can change, so check the current Gemini API pricing.
Configure another provider
Ollama
Follow the official Ollama quickstart, then enter the server address in Endpoint and the exact model name in Model. Ollama supports local and cloud models, so confirm where the selected model runs before enabling enhancement.
OpenAI or Anthropic
Create a provider key, paste it into API key, and choose a Model. Use the official OpenAI API quickstart or Anthropic API keys page for current account steps. Provider terms and billing apply.
Custom
Select Custom for a service that accepts OpenAI-compatible requests. Enter its Base URL, exact Model identifier, and API key, then enable enhancement. Obtain those values from the service's documentation.