llms.txt
+8 −2
https://www.assemblyai.com/llms.txt
− > AssemblyAI provides production-ready Voice AI models for speech-to-text, real-time streaming transcription, speaker diarization, Speech Understanding, Guardrails, Text-to-Speech, and the LLM Gateway. This file indexes the Markdown sources agents should prefer over crawling the HTML marketing site.− - [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview.md): apply leading LLMs to audio through one API.+ > AssemblyAI provides production-ready Voice AI models for speech-to-text, real-time streaming transcription, dictation (the Dictation API), speaker diarization, Speech Understanding, Guardrails, Text-to-Speech, and the LLM Gateway. This file indexes the Markdown sources agents should prefer over crawling the HTML marketing site.+ ## MCP Servers+ AssemblyAI runs two MCP servers. They do different jobs.+ - [AssemblyAI MCP server](https://www.assemblyai.com/docs/mcp-server.md): remote, Streamable HTTP, at https://mcp.assemblyai.com/mcp. Lets Claude, Cursor, VS Code and other MCP clients transcribe, summarize and analyze audio on the user's AssemblyAI account. Auth: sign in with AssemblyAI (OAuth) or `Authorization: Bearer YOUR_API_KEY`. Usage is billed at normal API rates. Use it when the user wants a task done, not code written.+ - [Docs MCP server](https://www.assemblyai.com/docs/coding-agent-prompts.md): https://www.assemblyai.com/docs/mcp. Free, no auth. Searches and reads the AssemblyAI docs so coding agents write correct code.+ - [Dictation API quickstart](https://www.assemblyai.com/docs/dictation.md): send-ready text from a spoken utterance in one call, with the verbatim transcript alongside.+ - [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart.md): apply leading LLMs to audio through one API.+ - [Dictation API](https://www.assemblyai.com/products/dictation-api.md)