AudioPod AI (core) — Claude Code MCP server: audio tools
A hosted MCP server for transcribing, splitting, cleaning, and converting audio you already have. Use it when an agent needs audio processing without local models.
claude mcp add --transport http audiopod-core https://mcp.audiopod.ai/coreWhat AudioPod AI (core) does
AudioPod AI (core) connects an agent to the remote endpoint https://mcp.audiopod.ai/core. Its tools can transcribe recordings with speaker labels and SRT/VTT subtitles, split tracks into stems, remove background noise, put speakers on separate tracks, convert media, and turn audio into MIDI. The core endpoint exposes 9 tools, including job, account, and profile checks.
Long-running operations return a job_id; the agent can query it with check_job_status. On the first use, the client opens an OAuth 2.1 sign-in window. CI and headless runs use an API key sent through X-API-Key. The service is remote, so local models and a GPU are not needed.
Core works with audio you already have and does not create new audio. Music generation and speech synthesis belong to the full endpoint instead.
What it helps with
- transcribe a recording with speaker labels
- produce SRT or VTT subtitles from audio
- split a track into vocal and instrumental stems
- remove background noise from a voice recording
- convert a recording into MIDI
Example prompts for the agent
- Transcribe
meeting.wav, label each speaker, and return an SRT file. - Remove background noise from
interview.m4awhile keeping the voice character. - Split
song.mp3into stems and report the job status.
How to install AudioPod AI (core)
Platform CLI: remote server
claude mcp add --transport http audiopod-core https://mcp.audiopod.ai/corePlatform CLI: remote server
codex mcp add audiopod-ai-core --url https://mcp.audiopod.ai/coreConfig file
{
"mcpServers": {
"audiopod-ai-core": {
"url": "https://mcp.audiopod.ai/core"
}
}
}Config file
{
"servers": {
"audiopod-ai-core": {
"type": "http",
"url": "https://mcp.audiopod.ai/core"
}
}
}Platform CLI: remote server
gemini mcp add -t http audiopod-ai-core https://mcp.audiopod.ai/coreStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about AudioPod AI (core)
How do I install AudioPod AI (core) in Claude Code?
Run these commands in order: claude mcp add --transport http audiopod-core https://mcp.audiopod.ai/core, then claude mcp add --transport http audiopod-ai-core https://mcp.audiopod.ai/core.
What does AudioPod AI (core) do?
It gives an agent tools for transcription, noise removal, speaker and stem separation, media conversion, and audio-to-MIDI conversion. It can also check long-running jobs and the connected account.
Does AudioPod AI (core) need an API key?
The client can open an OAuth 2.1 sign-in window on first use. CI and headless workflows use an API key in the X-API-Key header.
