Platform edition

OpenAI Compatible for Windows

Server profiles for transcription and text processing with any OpenAI-compatible server, such as Ollama, LM Studio, or vLLM.

Version: 1.1.3
Plugin ID: com.typewhisper.openai-compatible
Requirements: TypeWhisper 1.1.0 or newer · Windows 10 or newer · A local or remote OpenAI-compatible server; an API key only if the server requires one

Inside this edition

Speech-to-text through the configured local or remote server
LLM provider for workflow prompts, through Chat Completions or the Responses API
Multiple server profiles, each with its own URL, optional API key, models, and settings
Model suggestions from the server's model list, or any model ID entered by hand
Batch or realtime transcription, including deployment-scoped endpoints with an API version

Enter a Profile name and the Server URL, for example http://localhost:11434; the profile appears under this name as a provider
Enter an API key only if your server requires one, and select Test connection
Select Refresh models, then enter a Transcription model ID and a Text model ID; leave the transcription model empty for a text-only server
If your server needs it, adjust Transcription mode, Text API, Temperature, Thinking mode, and Text request timeout, then select Save profile
To connect another server, add a profile with + next to Server profile

Set up the add-on and verify its platform-specific capabilities with a first practical workflow.

Roles in TypeWhisper

TranscriptionLLM

In TypeWhisper, open Settings > Discover plugins and install OpenAI Compatible. The add-on then appears in the Settings sidebar, and its page opens. If it is already installed, open its page in the sidebar.
On the add-on's page, review the options available in this edition.
Enter a Profile name and the Server URL, for example http://localhost:11434; the profile appears under this name as a provider
Enter an API key only if your server requires one, and select Test connection
Select Refresh models, then enter a Transcription model ID and a Text model ID; leave the transcription model empty for a text-only server
If your server needs it, adjust Transcription mode, Text API, Temperature, Thinking mode, and Text request timeout, then select Save profile
To connect another server, add a profile with + next to Server profile
Under Settings > Dictation, select your server profile as the Provider and choose a Model. A Dictation Only workflow can also use its own transcription model.
In a workflow, select your server profile as the Provider under Advanced, or choose it as the Default LLM for workflows without a provider of their own.

Transcription: Dictate a few sentences with your server profile and check the language, model, and result before you use it for longer recordings.
LLM: Create a meeting-notes workflow, select your server profile as its LLM provider, and turn a short dictation into a summary, decisions, and action items.