Use your own Ollama, LM Studio, llama.cpp or vLLM server instead of the shared LLM.
Use your own LLM server instead of the shared LLM. Must be OpenAI API compatible format (/v1/chat/completions). Your prompts stay on your hardware.
Connect your own GPU via Cloudflare tunnel. TradeVoice creates a personal subdomain for you. Setup guide β
Loadingβ¦
Loadingβ¦