{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_uuy48kzftd4e","handle":"speaktome-mcp","url":"https://wellknown.network/agents/speaktome-mcp","links":{"self":"https://wellknown.network/agents/speaktome-mcp/record.json","html":"https://wellknown.network/agents/speaktome-mcp","markdown":"https://wellknown.network/agents/speaktome-mcp/record.md","api":"https://wellknown.network/api/v1/agents/speaktome-mcp","status":"https://wellknown.network/api/v1/agents/speaktome-mcp/status","claim":"https://wellknown.network/agents/speaktome-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/speaktome-mcp/claim.json","badge":"https://wellknown.network/agents/speaktome-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/speaktome-mcp/history","tools":"https://wellknown.network/api/v1/agents/speaktome-mcp/tools"},"ard":{"identifier":"urn:air::server:speaktome-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"speaktome-mcp","summary":"Local stdio MCP scaffold for microphone-to-whisper transcription","description":"# SpeakToMe MCP\n\nSpeakToMe MCP is a local Python MCP server for Linux. It records from a microphone on the same machine, transcribes rolling audio windows with a local `faster-whisper` `small` model, and can also speak local text through `espeak-ng`, all over stdio.\n\n## Scope\n\n- Linux only for v1\n- stdio transport only\n- local microphone capture through `sounddevice`\n- local transcription through `faster-whisper`\n- rolling duration based listening started by `start_listening(duration_seconds=...)`\n- transcript returned by `poll_transcription(session_id)` when the session is stopped\n- one active in-memory session at a time\n- local text to speech through `espeak-ng`\n\n## Prerequisites\n\nYou need:\n\n- Linux\n- Python 3.11 or newer\n- a working microphone input device\n- system audio libraries required by `sounddevice`, usually PortAudio plus ALSA or PipeWire user-space packages on Linux\n- `espeak-ng` installed if you want to use `speak_text`\n\nIf you want the `uv` workflow, install [`uv`](https://docs.astral.sh/uv/). If `sounddevice` cannot open devices, install the PortAudio runtime or development package used by your distro, then confirm your normal desktop audio stack is working. If `speak_text` fails, confirm `espeak-ng` is installed and available on `PATH` for the same Linux user session that starts the MCP host.\n\n## Install\n\n### Install from PyPI\n\n```bash\npip install speaktome-mcp\n```\n\n### Install from GitHub\n\n```bash\npip install git+https://github.com/alma3lol/SpeakToMeMCP.git\n```\n\n### Install from local source or an unpacked source archive\n\nDownload the repository source, or unpack a release source archive, then run:\n\n```bash\npip install .\n```\n\n### Install a development environment with uv\n\n```bash\nuv sync --locked --all-extras --dev\n```\n\n## Run and verify the CLI\n\nInstalled console script:\n\n```bash\nspeaktome-mcp --help\n```\n\nStart the server with the installed console script:\n\n```bash\nspeaktome-mcp\n```\n\nModule entrypoint fallback:\n\n```bash\npython -m speaktome_mcp --h…","publisher":{"name":"alma3lol","url":null},"homepage":"https://github.com/alma3lol/SpeakToMeMCP","repository":"https://github.com/alma3lol/SpeakToMeMCP","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:speaktome-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-recognition","name":"Speech Recognition","confidence":1,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":1,"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":"speaktome-mcp","registry":"pypi","observedAt":"2026-10-28T23:22:07.391Z","publishedAt":"2026-07-01T10:41:13.989988Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"speaktome-mcp","url":"https://pypi.org/project/speaktome-mcp/","firstSeenAt":"2026-09-10T12:23:09.482Z","fetchedAt":"2026-10-28T23:20:01.070Z","normalizedAt":"2026-10-28T23:20:01.070Z"}]},"firstSeenAt":"2026-09-10T12:23:09.482Z","updatedAt":"2026-10-28T23:22:07.391Z"}