LLM Providers

Post-processing uses Large Language Models (LLMs) to format and enhance your transcriptions.

Supported Providers

• OpenAI: GPT-4o, GPT-4o-mini
• Anthropic: Claude 3.5 Sonnet, Claude 3 Haiku
• Google: Gemini Pro
• Mistral: Mistral Large
• OpenRouter: Access to 100+ models
• Cerebras: Fast inference
• Ollama: Local models (Llama, Mistral, etc.)

Using Ollama (Local)

For complete privacy, use Ollama to run LLMs locally:

1. Install Ollama from ollama.ai
2. Pull a model (e.g., ollama pull llama3)
3. In Speakly, select Ollama as your LLM provider
4. Choose your downloaded model