@speechweave/mcp

Official Model Context Protocol server for SpeechWeave. Use to transcribe local files and URLs from Cursor, Claude Desktop, LM Studio, and other MCP clients.

SpeechWeave handles short clips and long-form audio without client-side chunking. This MCP server exposes both wait-first tools (get a transcript in one turn) and async create + poll tools (start a job, then check status).

Docs: speechweave.com/docs/mcp · API reference

Install / run

Requires Node.js 18+ and a SpeechWeave API key (sk_live_…).

export SPEECHWEAVE_API_KEY="sk_live_..."
npx -y @speechweave/mcp

Cursor / Claude Desktop

Add to your MCP config (e.g. .cursor/mcp.json, claude_desktop_config.json):

{
	"mcpServers": {
		"speechweave": {
			"command": "npx",
			"args": ["-y", "@speechweave/mcp"],
			"env": {
				"SPEECHWEAVE_API_KEY": "sk_live_..."
			}
		}
	}
}

Tools

Tool	Mode	When to use
transcribe_file	Wait-first	Absolute local path; wait until transcript is ready
transcribe_url	Wait-first	Public HTTPS URL; wait until transcript is ready
start_job_file	Async	Absolute local path; return job_id immediately
start_job_url	Async	Public HTTPS URL; return job_id immediately
get_job_status	Poll	Fetch status / transcript for a job id
cancel_job	Control	Cancel a queued or processing job

Never pass raw audio bytes over MCP. Use absolute file paths (local clients) or HTTPS URLs.

Configuration & Arguments

All transcription tools accept the following optional arguments:

• model: Choose core (default) or max.
• service_mode: Choose deferred (default) or synchronous.
• language: Optional ISO language code to force language detection.

Timeout behavior: Wait-first tools accept an optional timeout_ms. If the transcription exceeds the timeout, the tool gracefully returns a job_id and instructs the client to switch to get_job_status polling.

Example Prompts

After adding the server and restarting your client, try asking your AI assistant:

Short clip (wait-first)

"Use SpeechWeave to transcribe /Users/me/recordings/standup.mp3 and summarize action items."

The assistant will call transcribe_file with the absolute path and summarize the returned transcript.

Long podcast (async + poll)

"Start a SpeechWeave job for https://cdn.example.com/three_hour_podcast.mp3, then check back until it completes."

The assistant will call start_job_url, then periodically call get_job_status until the status reaches completed.