agent-fm is an open-source MCP server that provides text-to-speech functionality for AI agents. It allows developers to add voice output to their agents, making them capable of spoken communication. Suitable for AI developers and robotics projects.
In the Voice, TTS & speech space, agent-fm takes a focused approach. It focuses on enabling AI agents to communicate via synthesized voice using text-to-speech. agent-fm is an open-source project aimed at AI developers building voice-enabled agents. The project is open source (MIT). agent-fm is available on the command line, and it can be self-hosted.
anthropics builds and maintains agent-fm, and the product first shipped in 2026. Across PulseGate's embedding index, agent-fm has few near neighbours, marking it as relatively distinct. Among its 3 catalogued features are text-to-speech, MCP server, and voice output for agents. It exposes integrations via an MCP server.
Latest indexed changes and source events
Other apps tracked under the same category.
