OpenAI GPT BYOK configuration
Oyma provides native integration for OpenAI’s API, allowing you to run meeting summaries and Ask conversational queries using GPT-4o with your personal or enterprise credentials.
Step-by-step OpenAI setup
1. Generate an API key
- Navigate to the OpenAI Platform (
platform.openai.com). - Go to Dashboard › API Keys and click Create new secret key.
- Copy the key string (begins with
sk-proj-...).
2. Configure Oyma
- Open Settings › AI › Provider.
- Select OpenAI (Cloud BYOK).
- Paste your key into the API Key field.
- Click Save to Keychain.
- Select your model:
- GPT-4o: Recommended for comprehensive meeting minutes and deep analysis.
- GPT-4o-mini: High-speed, economical model for rapid daily summaries.
- Click Test Connection.
Zero proxy architecture
Calls travel directly from your Mac to api.openai.com:443. No intermediary servers, third-party relays, or analytics aggregators see your meeting text. You can inspect every outbound request in the Egress log.
Related guides
- General BYOK guide in Bring your own AI API keys.
- Anthropic setup in Anthropic Claude BYOK configuration.
- Audit network activity in Egress log.
Questions
Which OpenAI models are supported?
Oyma supports GPT-4o, GPT-4o-mini, and o1 models.
Where is my OpenAI API key saved?
Keys are saved in your macOS login Keychain via Apple's Security.framework with encrypted hardware protection.
Does OpenAI train models on API inputs?
Under OpenAI's standard commercial API terms, data submitted via the API is not used for model training.
