$ loading_
Enable AI agents to capture microphone audio and convert speech to text.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.decibri/mcp-listen" MCP server from askskill: Run: claude mcp add 'io-github-decibri-mcp-listen' -- npx -y mcp-listen
Use the microphone to listen to my speech and transcribe it into English text in real time, with one sentence per line.
A sentence-by-sentence speech transcription.
Start microphone capture, convert my spoken meeting content into text, and organize it into bullet points.
A transcription plus a summarized bullet list of key points.
Listen to my voice command, convert it to text, then act on it: first record the task, then repeat what I just said.
The spoken command is transcribed first, then the agent performs follow-up actions based on the text.
Developers can connect this MCP tool to an agent so it can listen to microphone input and turn speech into text for downstream chat or task handling.
When typing is inconvenient, users can dictate through a microphone so the agent can transcribe speech first and then process the text.
It is an MCP tool that gives AI agents the ability to listen. Based on the description, it supports microphone capture and speech-to-text.
From the name and description, it uses a microphone as the audio input source and converts captured speech into text.
No documentation excerpt is provided, so installation steps, dependencies, and key requirements cannot be confirmed. For integration details, see the source repository.
Let AI agents turn text into natural speech with automatic voice engine fallback.
Create, configure, and manage ElevenLabs conversational AI voice agents visually.
Connect AI agents to HyperWhisper for transcription, model control, and recording search.
Enable AI agents to handle phone, SMS, and email via one MCP endpoint.
Convert text and speech with voice listing, TTS, and transcription tools.
Make AI speak text aloud with macOS TTS, queueing, and blocking control.