Skip to main content
Glama

audio_transcribe

Convert audio files from URLs to text transcripts using AI transcription. Specify language for accurate results.

Instructions

Transcribe audio from a URL using Whisper AI ($0.003/min)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesURL of audio file (mp3/mp4/wav/ogg/webm)
languageNoLanguage code (e.g. en, pt)en

Implementation Reference

  • index.js:26-26 (registration)
    Registration of the audio_transcribe tool within the TOOLS array.
    { name: 'audio_transcribe', description: 'Transcribe audio from a URL using Whisper AI', inputSchema: { type: 'object', properties: { url: { type: 'string', description: 'URL of audio file (mp3/mp4/wav/ogg/webm)' }, language: { type: 'string', description: 'Language code (e.g. en, pt)', default: 'en' } }, required: ['url'] }, endpoint: '/audio/transcribe', price: '$0.003/min' },
  • index.js:94-115 (handler)
    The main handler that dispatches calls to the appropriate tool endpoint using the callTool helper.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      const { name, arguments: args } = request.params;
      
      if (!API_KEY) {
        return {
          content: [{ type: 'text', text: 'Error: ITERATOOLS_API_KEY environment variable not set. Get a key at https://iteratools.com' }],
          isError: true,
        };
      }
      
      const tool = TOOLS.find(t => t.name === name);
      if (!tool) {
        return { content: [{ type: 'text', text: `Unknown tool: ${name}` }], isError: true };
      }
      
      try {
        const result = await callTool(tool.endpoint, args);
        return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
      } catch (err) {
        return { content: [{ type: 'text', text: `Error: ${err.message}` }], isError: true };
      }
    });
  • The callTool helper function that performs the actual network request to the IteraTools API based on the tool's defined endpoint.
    async function callTool(endpoint, params) {
      const fetch = (await import('node-fetch')).default;
      const isGet = ['GET'].includes((TOOLS.find(t => t.endpoint === endpoint) || {}).method);
      
      const url = isGet 
        ? `${BASE_URL}${endpoint}?${new URLSearchParams(params)}`
        : `${BASE_URL}${endpoint}`;
      
      const res = await fetch(url, {
        method: isGet ? 'GET' : 'POST',
        headers: {
          'Content-Type': 'application/json',
          'Authorization': `Bearer ${API_KEY}`,
        },
        body: isGet ? undefined : JSON.stringify(params),
      });
      
      const text = await res.text();
      let data;
      try { data = JSON.parse(text); } catch { data = { raw: text }; }
      
      if (!res.ok) {
        if (res.status === 402) {
          throw new Error(`Insufficient credits. Add credits at https://iteratools.com. Cost: ${TOOLS.find(t=>t.endpoint===endpoint)?.price || 'see docs'}`);
        }
        throw new Error(`API error ${res.status}: ${text.substring(0, 200)}`);
      }
      
      return data;
    }
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It successfully discloses cost ('$0.003/min') and technology ('Whisper AI'), but omits critical behavioral details: output format (plain text vs. JSON with timestamps), maximum file duration, supported file size limits, or error handling for invalid URLs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 10 words. Every element earns its place: action (Transcribe), resource (audio), constraint (from a URL), implementation (Whisper AI), and cost ($0.003/min). No redundant or filler text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter tool with 100% schema coverage and no nested objects, the description is minimally adequate. However, the absence of an output schema creates a gap—the description should ideally specify what the tool returns (e.g., transcribed text string, confidence scores) but does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with 'url' and 'language' fully documented in the schema. The description reinforces the URL requirement but does not add syntax details, format constraints, or usage guidance for the parameters beyond what the schema already provides, warranting the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description provides specific verb (Transcribe), resource (audio), source constraint (from a URL), and distinguishes from siblings (e.g., image_ocr, tts) by specifying audio input. The addition of 'Whisper AI' and pricing '$0.003/min' further clarifies scope and mechanism.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'from a URL' implies the tool requires a hosted audio file, not local/uploaded files, providing implicit usage context. However, there are no explicit when-to-use guidelines, exclusions, or comparisons to alternatives like image_ocr for visual text extraction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fredpsantos33/itera-tools-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server