SpeechWeave runs on your own machine — the client starts it, so there is no endpoint to ping. 58 installs a week from npm. Last commit 21 Aug 2026.
Transcribe local files and URLs with SpeechWeave's OpenAI-compatible API.
Today is the operative word: we check SpeechWeave 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 mcp -- npx -y @speechweave/mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@speechweave/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@speechweave/mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@speechweave/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@speechweave/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SPEECHWEAVE_API_KEY (SpeechWeave API key (sk_live_...)).
The author declared them in the registry entry; get the values from the project itself.
Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.
Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.
Convert text to speech, transcribe audio, and dub videos with AI voices
Thai and English speech AI: TTS with local playback, transcription, translation to Thai, and OCR
Transcribe and understand local audio/video with CrispASR and local models only.
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
Analyze any video (local file or URL) into frames + transcript for Claude Code
Answers built from our own checks of this server.