@speechweave/mcp

Official Model Context Protocol server for SpeechWeave. Use to transcribe local files and URLs from Cursor, Claude Desktop, Claude Code, Windsurf, 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

Related MCP server: whisper-transcribe-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

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

Configuration & Arguments

All transcription and job-start 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.

• task: Choose transcribe (default) or translate to produce an English translation instead; language is ignored when translating.

• prompt: Optional custom vocabulary hint (proper nouns, acronyms, product names) for the first ~30s of audio.

Formatted transcripts: transcribe_file, transcribe_url, and get_job_status also accept an optional response_format (text, srt, vtt, or verbose_json) to return the transcript in that shape instead of the default plain text.

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.

Translate to subtitles (wait-first)

"Translate /Users/me/recordings/spanish_interview.mp3 into English SRT subtitles using SpeechWeave."

The assistant will call transcribe_file with task: "translate" and response_format: "srt".