Whipscribe MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 158 installs a week from pypi. Last commit 7 Oct 2026.
Transcribe audio/video files or URLs via the WhipScribe cloud API and fetch the transcript.
Today is the operative word: we check Whipscribe MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add whipscribe-mcp -- uvx whipscribe-mcp
{
"mcpServers": {
"whipscribe-mcp": {
"args": [
"whipscribe-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.whipscribe-mcp]
command = "uvx"
args = ["whipscribe-mcp"]
{
"mcpServers": {
"whipscribe-mcp": {
"args": [
"whipscribe-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"whipscribe-mcp": {
"args": [
"whipscribe-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
WHIPSCRIBE_API_KEY (WhipScribe API key (optional; unlocks paid quota, the anonymous free tier works without it)).
The author declared them in the registry entry; get the values from the project itself.
Analyze any video (local file or URL) into frames + transcript for Claude Code
Fetch YouTube video transcripts individually or in bulk via get_transcript and get_bulk_transcripts.
Transcribe audio and video files to text, SRT and VTT subtitles in 99 languages with Whisper.
Transcribe any audio or video URL to text, SRT and VTT, with chunking and only-new episodes
Transcribe Russian audio and video with timestamps and optional speaker labels from files or links.
Transcribe audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A.
Cut audio from YouTube, TikTok or Instagram links to MP3/WAV, and fetch video transcripts.
Private audio and video transcription with Whisper on your own computer, on the GPU or CPU.
Answers built from our own checks of this server.