extract-audio
Extract structured data from audio files using a prompt. Convert spoken content into organized information for analysis and processing.
Instructions
Extract structured data from audio files based on a prompt.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| inputMethod | Yes | Input method | |
| audio | Yes | URL or base64-encoded audio | |
| prompt | Yes | Extraction prompt | |
| jsonMode | No | Return in JSON format |
Implementation Reference
- src/index.ts:735-756 (handler)The handler function for the 'extract-audio' tool. It proxies the request to an external API endpoint at `${NWS_API_BASE}/api/v1/extract-audio`, passing the input parameters and returning the JSON response as text content.
async ({ inputMethod, audio, prompt, jsonMode }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/extract-audio`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ inputMethod, audio, prompt, jsonMode, requestSource: "mcp", }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; } - src/index.ts:729-734 (schema)Zod input schema defining the parameters for the 'extract-audio' tool: inputMethod (url or base64), audio (URL or base64), prompt, and optional jsonMode.
{ inputMethod: z.enum(["url", "base64"]).describe("Input method"), audio: z.string().describe("URL or base64-encoded audio"), prompt: z.string().describe("Extraction prompt"), jsonMode: z.boolean().optional().describe("Return in JSON format"), }, - src/index.ts:726-757 (registration)Full registration of the 'extract-audio' tool via server.tool(), including name, description, input schema, and handler function.
server.tool( "extract-audio", "Extract structured data from audio files based on a prompt.", { inputMethod: z.enum(["url", "base64"]).describe("Input method"), audio: z.string().describe("URL or base64-encoded audio"), prompt: z.string().describe("Extraction prompt"), jsonMode: z.boolean().optional().describe("Return in JSON format"), }, async ({ inputMethod, audio, prompt, jsonMode }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/extract-audio`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ inputMethod, audio, prompt, jsonMode, requestSource: "mcp", }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; } );