#Cloud AI for Summaries

Clearminutes can use cloud AI providers to generate meeting summaries. All cloud providers require an API key from the provider — your key goes directly from Clearminutes to their API, nothing passes through Clearminutes servers.

#Where to Configure

Open Settings → Summary and choose a provider from the dropdown.

---

#Claude (Anthropic)

Claude produces high-quality, detailed summaries and is a strong choice for long or complex meetings.

#Get an API Key

1. Go to console.anthropic.com
2. Sign up or log in
3. Navigate to API Keys → Create Key
4. Copy the key (it starts with sk-ant-...)

#Configure in Clearminutes

1. Open Settings → Summary
2. Select Claude from the provider dropdown
3. Paste your API key
4. Choose a model:

5. Click Save

---

#Groq

Groq is extremely fast due to custom inference hardware. Ideal if you want near-instant summaries.

#Get an API Key

1. Go to console.groq.com
2. Sign up or log in
3. Navigate to API Keys → Create API Key
4. Copy the key

#Configure in Clearminutes

1. Open Settings → Summary
2. Select Groq from the provider dropdown
3. Paste your API key
4. Choose a model — Llama 3.3 70B is recommended for quality
5. Click Save

---

#OpenAI

Use GPT-4o or GPT-4.1 for reliable, high-quality summaries.

#Get an API Key

1. Go to platform.openai.com
2. Sign up or log in
3. Navigate to API Keys → Create new secret key
4. Copy the key (it starts with sk-...)

#Configure in Clearminutes

1. Open Settings → Summary
2. Select OpenAI from the provider dropdown
3. Paste your API key
4. Choose a model:

5. Click Save

---

#OpenRouter

OpenRouter gives you access to hundreds of models (Claude, Llama, Mistral, Gemini, and more) through a single API key. Good if you want to experiment with different models.

#Get an API Key

1. Go to openrouter.ai
2. Sign up or log in
3. Navigate to Keys → Create Key
4. Copy the key

#Configure in Clearminutes

1. Open Settings → Summary
2. Select OpenRouter from the provider dropdown
3. Paste your API key
4. Choose a model from the list (Clearminutes fetches available models from OpenRouter automatically)
5. Click Save

---

#Custom OpenAI-Compatible Server

If you run your own inference server (LM Studio, vLLM, llama.cpp server, etc.) that exposes an OpenAI-compatible API, you can connect it here.

#Configure in Clearminutes

1. Open Settings → Summary
2. Select Custom Server (OpenAI-compatible) from the provider dropdown
3. Enter your Endpoint URL — must start with http:// or https://
   • Example: http://localhost:8000/v1
   • Example: http://192.168.1.50:8080/v1
4. Enter the Model Name as your server expects it (e.g. llama-3-70b, mistral-7b)
5. Optionally enter an API Key if your server requires one (can be left blank)
6. Expand Advanced Options to set:
   • Max Tokens (minimum 1)
   • Temperature (0.0–2.0)
   • Top P (0.0–1.0)
7. Click Test Connection to verify Clearminutes can reach the server
8. Click Save

---

#Switching Providers

You can change provider at any time in Settings → Summary. The new provider is used for all summaries generated after saving. Previous summaries are not regenerated.

#Troubleshooting

"Invalid API key" or authentication error

• Double-check you copied the full key with no leading/trailing spaces
• Make sure the key is active and not revoked in the provider's dashboard

Summaries are empty or very short

• Some free-tier keys have low token limits — check your provider's dashboard for quota usage

Custom server: "Connection failed"

• Confirm the server is running and reachable from your machine
• Check the endpoint URL includes the correct path (e.g. /v1 for OpenAI-compatible servers)
• Try the URL in your browser — you should see a response (even an error) if the server is up

#Related

• Ollama Setup — run models entirely locally with no API key
• Built-in AI — offline summaries with no setup required
• Generate Summaries — how to trigger and configure summaries