{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_dz66snfd9n95","handle":"glados-voice-mcp","url":"https://wellknown.network/agents/glados-voice-mcp","links":{"self":"https://wellknown.network/agents/glados-voice-mcp/record.json","html":"https://wellknown.network/agents/glados-voice-mcp","markdown":"https://wellknown.network/agents/glados-voice-mcp/record.md","api":"https://wellknown.network/api/v1/agents/glados-voice-mcp","status":"https://wellknown.network/api/v1/agents/glados-voice-mcp/status","claim":"https://wellknown.network/agents/glados-voice-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/glados-voice-mcp/claim.json","badge":"https://wellknown.network/agents/glados-voice-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/glados-voice-mcp/history","tools":"https://wellknown.network/api/v1/agents/glados-voice-mcp/tools"},"ard":{"identifier":"urn:air::server:glados-voice-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"glados-voice-mcp","summary":"Warm, shared GLaDOS text-to-speech server with an MCP interface for agents","description":"# glados-voice-mcp\n\nA warm, shared GLaDOS text-to-speech server for agents, exposed as an [MCP](https://modelcontextprotocol.io) tool.\nIt builds on [nimaid/GLaDOS-TTS](https://github.com/nimaid/GLaDOS-TTS), included unmodified as a git submodule.\n\n> **Using an AI agent?** Point it at this repository and ask it to follow [`AGENTS.md`](AGENTS.md); it contains every step to install, register and verify the server.\n\n- **Fast:** about 100 ms to first audio once the models are loaded; text is split into sentences and the first one plays while the rest is still being synthesized.\n- **Lazy and shared:** the MCP process is a thin proxy. The first `speak` starts one shared daemon (`127.0.0.1:18765`) that loads the models, serves every agent on one audio device, and exits after 10 minutes without requests or speech.\n- **In character:** the persona is part of the tool description and `speak` rejects calls with `in_character=false`. The server cannot verify the style of the text itself.\n- **One voice at a time:** if a message is loading or playing, `speak` returns `BUSY ... Retry in about N seconds` so agents never talk over each other. `speak` with empty text cuts speech for everyone.\n\n## Install\n\nNo clone or project directory is needed: [uv](https://docs.astral.sh/uv/) installs the [`glados-voice-mcp`](https://pypi.org/project/glados-voice-mcp/) package from PyPI. Pick exactly one onnxruntime extra: `cpu` or `cuda` (NVIDIA, CUDA 13 wheels).\n\n```bash\n# 1. Build the environment and download the models once (about 125 MB, stored in your user data dir)\nuvx --from \"glados-voice-mcp[cpu]@latest\" glados-voice download-models\n\n# 2. Try it (plays audio)\nuvx --from \"glados-voice-mcp[cpu]@latest\" glados-voice say \"Hello, test subject.\"\n```\n\nPrefer a persistent command? `uv tool install \"glados-voice-mcp[cpu]\"` or `pipx install \"glados-voice-mcp[cpu]\"` puts `glados-voice-mcp` on your `PATH`. To develop, clone with `git clone --recurse-submodules https://github.com/bkmeneguello/glados-voi…","publisher":{"name":"Bruno Meneguello","url":null},"homepage":"https://github.com/bkmeneguello/glados-voice-mcp","repository":"https://github.com/bkmeneguello/glados-voice-mcp","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp","model-context-protocol","tts","text-to-speech","glados","voice","agents"],"pricing":null,"endpoints":[{"url":"pypi:glados-voice-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"media.speech-synthesis","name":"Speech Synthesis","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"glados-voice-mcp","registry":"pypi","observedAt":"2026-11-09T06:27:27.756Z","publishedAt":"2026-10-31T21:34:19.573500Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"glados-voice-mcp","url":"https://pypi.org/project/glados-voice-mcp/","firstSeenAt":"2026-11-03T03:26:27.875Z","fetchedAt":"2026-11-09T06:25:40.186Z","normalizedAt":"2026-11-09T06:25:40.186Z"}]},"firstSeenAt":"2026-11-03T03:26:27.875Z","updatedAt":"2026-11-09T06:27:27.756Z"}