> ## Documentation Index > Fetch the complete documentation index at: https://easy-peasy.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create Transcription > Programmatically create [AI Transcriptions](https://easy-peasy.ai/audios) from audio files. ## Complete workflow Transcription is asynchronous — after submitting an audio file, you need to poll for results. Here's the full workflow: ### Step 1: Submit audio for transcription Submit a publicly downloadable audio URL with this endpoint. A paid subscription and remaining monthly transcription allowance are required. The response includes a `uuid` you'll need for the next steps. Transcription typically takes **1–5 minutes** depending on audio length. Save the `uuid` from the response. ### Step 2: Poll for results Use [Get Transcription Result](/docs/api-reference/endpoint/get-transcription) with the same account's API key. **Poll every 15–30 seconds** while `transcription_status` is `processing`. API-key responses return `content`, `segments`, and `transcription_status` **at the top level**, without an `audio` wrapper. `done` means complete even if no speech was detected and `content` is empty. Stop on `failed`. Older records may contain transcript text without a status. The following Node.js 20+ example stops after ten minutes. Keep the UUID if it times out so you can check the existing job later. ```javascript theme={null} async function waitForTranscription(uuid, apiKey) { const deadline = Date.now() + 10 * 60 * 1000; while (Date.now() < deadline) { const response = await fetch('https://easy-peasy.ai/api/audios', { method: 'POST', headers: { 'Content-Type': 'application/json', 'x-api-key': apiKey, }, body: JSON.stringify({ audio_id: uuid }), signal: AbortSignal.timeout(Math.max(1, Math.min(30000, deadline - Date.now()))), }); const data = await response.json().catch(() => null); if (!response.ok) { throw new Error(`Transcription ${uuid}: HTTP ${response.status}: ${data?.error || 'Could not retrieve transcription'}`); } if (!data || data.uuid !== uuid) { throw new Error(`Unexpected response for transcription ${uuid}`); } if (data.transcription_status === 'failed') { throw new Error(`Transcription ${uuid} failed`); } if (data.transcription_status === 'done' || (!data.transcription_status && data.content)) { return data; } if (data.transcription_status && data.transcription_status !== 'processing') { throw new Error(`Unknown transcription status: ${data.transcription_status}`); } await new Promise(resolve => setTimeout(resolve, Math.max(0, Math.min(15000, deadline - Date.now())))); } throw new Error(`Timed out waiting for transcription ${uuid}. Keep this UUID and check it later.`); } ``` ### Step 3: Generate AI content (optional) Once the transcription is complete, use [Generate Audio Content](/docs/api-reference/endpoint/generate-audio-content) to create summaries, titles, action items, and more. ```bash theme={null} curl -X POST https://easy-peasy.ai/api/generate-audio-content \ -H "Content-Type: application/json" \ -H "x-api-key: YOUR_API_KEY" \ -d '{"audio_id": "YOUR_AUDIO_UUID"}' ``` You can also generate specific fields only: ```bash theme={null} curl -X POST https://easy-peasy.ai/api/generate-audio-content \ -H "Content-Type: application/json" \ -H "x-api-key: YOUR_API_KEY" \ -d '{ "audio_id": "YOUR_AUDIO_UUID", "fields": ["summary", "title", "keywords"] }' ``` **Content generated depends on the audio type:** | Audio Type | Fields | | ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Meeting** | summary, title, description, action items, keywords, timestamped overview, topics & bullets, LinkedIn post | | **Podcast** | summary, title, description, show notes, Twitter thread, article, newsletter, keywords, questions, LinkedIn post, timestamped overview, topics & bullets | | **Therapy Session** | summary, title, description, progress note, SOAP note, DAP note, keywords, timestamped overview, topics & bullets, LinkedIn post | ## OpenAPI ````yaml POST /api/transcriptions openapi: 3.0.1 info: title: Easy-Peasy.AI API description: >- API for Easy-Peasy.AI text, image, video, audio, and chat features. Authenticate with an API key from https://easy-peasy.ai/settings/api. Individual endpoints document public access and alternative authentication methods. version: 1.0.5 servers: - url: https://easy-peasy.ai security: - apiKeyAuth: [] paths: /api/transcriptions: post: summary: Create Transcription description: >- Programmatically create [AI Transcriptions](https://easy-peasy.ai/audios) from audio files. operationId: createTranscription requestBody: description: The audio parameters to create transcriptions required: true content: application/json: schema: $ref: '#/components/schemas/TranscriptionRequest' responses: '200': description: Successful transcription creation content: application/json: schema: $ref: '#/components/schemas/TranscriptionResponse' '400': description: Bad request - missing required fields or invalid values content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Invalid input '401': description: Missing or invalid API key, or blocked account. content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: Paid subscription required or monthly transcription limit reached. content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Server error components: schemas: TranscriptionRequest: type: object required: - url properties: audio_type: type: string description: The type of audio (e.g., podcast, meeting) example: podcast language: type: string description: The language of the audio (e.g., English, Chinese, French) example: English name: type: string description: The name of the transcription example: Interview with John Doe detect_speakers: type: boolean description: Whether to detect multiple speakers example: true default: true enhanced_quality: type: boolean description: Whether to use enhanced quality for transcription example: true url: type: string description: The URL of the audio file example: https://example.com/audiofile.mp3 TranscriptionResponse: type: object properties: uuid: type: string description: Unique identifier for the created transcription example: 4bc4e8ee-f29e-4a53-996e-5da955c42927 dashboard_url: type: string description: URL of the generated transcription example: https://easy-peasy.ai/audios/4bc4e8ee-f29e-4a53-996e-5da955c42927 Error: type: object properties: error: oneOf: - type: string - type: object properties: message: type: string status: type: integer description: >- Error text, or an object with message and optional status for some provider integrations. example: Invalid API key securitySchemes: apiKeyAuth: type: apiKey in: header name: x-api-key description: >- API key for authentication. Get yours at https://easy-peasy.ai/settings/api ````