> ## Documentation Index > Fetch the complete documentation index at: https://docs.musicgpt.com/llms.txt > Use this file to discover all available pages before exploring further. # Audio Transcribe > Processes an audio file to generate a transcription of the spoken content with support for language detection, translation, and multiple output formats. Convert your audio recordings into high-accuracy text using AI. **Audio Transcribe** enables seamless transcription for podcasts, interviews, lectures, meetings, and more. * Fast and accurate speech-to-text conversion * Supports multiple languages * Instant or asynchronous transcription with webhook support Audio Transcribe ensures reliable, professional-grade transcripts for your audio content. *** ## Endpoint ```http theme={null} POST /audio_transcribe ``` Use this endpoint to transcribe audio recordings into text. *** ## Sample Output Transcript Output of Charlie Puth and Wiz Khalifa's See You Again: > "It's been a long day without you, my friend, and I'll tell you all about it when I see you again. We've come a long way from where we began. Oh, I'll tell you all about it when I see you again, when I see you again. Damn, you know, all the planes we flew, good things we've been through. And I'll be standing right here talking to you about another pap. I know we love to hit the road and laugh, but something told me that it wouldn't last. Had to switch up, looking things different, see the bigger picture. Those were the days, hard work for ever pays. Now I see you in a better place. See you in a better place. Oh, after we not talk about family, we family is all that we got. Everything I would do, you would stand in there by my side. And now you've got me with me for the last ride. It's been a long day without you, my friend, and I'll tell you all about it when I see you again. We've come a long way from where we began. Oh, I'll tell you all about it when I see you again, when I see you again. First you both go out your way and the vibe is feeling stronger. It was small, turned to a friendship, but friendship turned to a bond. And that bond will never be broken. The love will never get lost. And when brotherhood comes first, then the land will never be crossed. It's never stood on our own when that land had to be drawn. And that land is where we reach. So remember me when I'm gone. How can we not talk about family, we family is all that we got. Everything I would do, you would stand in there by my side. And now you've got me with me for the last ride. Let the light go on your way. Hold every memory as you go. And every road you take will always be true. Oh, it's been a long day without you, my friend. And I'll tell you all about it when I see you again. We've come a long way from where we began. Oh, I'll tell you all about it when I see you again. When I see you again. Oh, I'll tell you all about it when I see you again. Oh, I'll tell you all about it when I see you again." *** ## Try it Yourself Visit the [Audio Transcribe Endpoint Explorer](/api-documentation/endpoint/audio_transcribe) to upload audio files and get instant transcripts. > 🚀 Try uploading different languages or noisy audio recordings to test the transcription quality! *** ## Request Parameters | Parameter | Type | Required | Description | | ------------- | ------ | -------- | ------------------------------------------------------------ | | `audio_url` | String | Yes | URL to the audio file you want to transcribe | | `language` | String | Optional | Language code (e.g., `en`, `es`, `fr`) for targeted accuracy | | `webhook_url` | String | Optional | Webhook URL to receive the transcription asynchronously | | `user_id` | String | Optional | Optional user ID for tracking purposes | > **content-type:** multipart/form-data *** ## Sample Request ### Python ```python theme={null} import requests url = "https://api.musicgpt.com/api/public/v1/audio_transcribe" headers = {"Authorization": "<<>>"} # Option 1: URL payload = { "audio_url": "https://example.com/audio.mp3", "language": "en", "translate": True, "transcription_format": "srt", "word_timestamps": True } response = requests.post(url, headers=headers, data=payload) print(response.json()) # Option 2: File Upload # payload = { # "language": "en", # "translate": False, # "transcription_format": "plain_text", # "word_timestamps": True # } # with open("audio.mp3", "rb") as f: # files = {"audio_file": f} # response = requests.post(url, headers=headers, data=payload, files=files) # print(response.json()) ``` *** ## Sample Response ### Success (200 OK) ```json theme={null} { "success":true, "task_id":"cade1dea-a9fb-49d3-a5b2-52f786ea5ad3", "conversion_id":"1c5a2543-5b99-499c-8bb4-28424497e60f", "eta":46, "credit_estimate":19.833, "message":"", "status":"IN_QUEUE" } ``` *** ## Webhook Response When transcription completes, your webhook will receive: ```json theme={null} { "success": true, "conversion_type": "Audio Transcription", "task_id": "cade1dea-a9fb-49d3-a5b2-52f786ea5ad3", "conversion_id": "1c5a2543-5b99-499c-8bb4-28424497e60f", "transcription": "It's been a long day without you, my friend, and I'll tell you all about it when I see you again. We've come a long way from where we began. Oh, I'll tell you all about it when I see you again, when I see you again. Damn, you know, all the planes we flew, good things we've been through. And I'll be standing right here talking to you about another pap. I know we love to hit the road and laugh, but something told me that it wouldn't last. Had to switch up, looking things different, see the bigger picture. Those were the days, hard work for ever pays. Now I see you in a better place. See you in a better place. Oh, after we not talk about family, we family is all that we got. Everything I would do, you would stand in there by my side. And now you've got me with me for the last ride. It's been a long day without you, my friend, and I'll tell you all about it when I see you again. We've come a long way from where we began. Oh, I'll tell you all about it when I see you again, when I see you again. First you both go out your way and the vibe is feeling stronger. It was small, turned to a friendship, but friendship turned to a bond. And that bond will never be broken. The love will never get lost. And when brotherhood comes first, then the land will never be crossed. It's never stood on our own when that land had to be drawn. And that land is where we reach. So remember me when I'm gone. How can we not talk about family, we family is all that we got. Everything I would do, you would stand in there by my side. And now you've got me with me for the last ride. Let the light go on your way. Hold every memory as you go. And every road you take will always be true. Oh, it's been a long day without you, my friend. And I'll tell you all about it when I see you again. We've come a long way from where we began. Oh, I'll tell you all about it when I see you again. When I see you again. Oh, I'll tell you all about it when I see you again. Oh, I'll tell you all about it when I see you again. You", "translation": null, "detected_language": "en", "message": "Transcription Completed" } ``` > 🔊 If no webhook is provided, you can fetch the transcript manually later using the `conversion_id`. *** ## Payload and Request Formation ## OpenAPI ````yaml POST /v1/audio_transcribe openapi: 3.1.0 info: title: Musicgpt API version: 1.0.0 description: API for retrieving conversion details by ID. servers: - url: https://api.musicgpt.com/api/public description: Production server security: [] paths: /v1/audio_transcribe: post: summary: Transcribe Audio to Text description: >- Processes an audio file to generate a transcription of the spoken content with support for language detection, translation, and multiple output formats. requestBody: required: true content: multipart/form-data: schema: type: object properties: audio_url: type: string description: URL of the audio file to transcribe. example: https://example.com/audio.mp3 audio_file: type: string format: binary description: Audio file to upload and process directly. language: type: string description: Language spoken in the audio (empty for auto-detection). example: en translate: type: boolean description: Whether to translate the transcription to English. example: false transcription_format: type: string description: Format of the transcribed output. enum: - plain_text - formatted_text - srt - vtt example: plain_text translation_format: type: string description: Format of the translated output (currently unused). enum: - plain_text - formatted_text - srt - vtt example: plain_text word_timestamps: type: boolean description: Whether to include word-level timestamps. example: false webhook_url: type: string description: Callback URL for async processing results. example: http://your-webhook-url.com/callback anyOf: - required: - audio_url - required: - audio_file responses: '200': description: Successfully initiated transcription content: application/json: schema: type: object properties: success: type: boolean task_id: type: string conversion_id: type: string eta: type: integer credit_estimate: type: number format: float message: type: string example: success: true task_id: transcribe123 conversion_id: conv456 eta: -1 credit_estimate: 100.1 message: Successfully published to queue '422': description: Validation Error content: application/json: schema: type: object properties: success: type: boolean example: false error: type: string example: Either audio_url or audio_file must be provided. '500': description: Server Error content: application/json: schema: type: object properties: success: type: boolean example: false error: type: string example: Internal Server Error security: - ApiKeyAuth: [] x-codeSamples: - lang: Python source: >- import requests url = "https://api.musicgpt.com/api/public/v1/audio_transcribe" headers = {"Authorization": "<<>>"} # Option 1: URL payload = { "audio_url": "https://example.com/audio.mp3", "language": "en", "translate": True, "transcription_format": "srt", "word_timestamps": True } response = requests.post(url, headers=headers, data=payload) print(response.json()) # Option 2: File Upload # payload = { # "language": "en", # "translate": False, # "transcription_format": "plain_text", # "word_timestamps": True # } # with open("audio.mp3", "rb") as f: # files = {"audio_file": f} # response = requests.post(url, headers=headers, data=payload, files=files) # print(response.json()) - lang: PHP source: |- >>']; // Option 1: URL $data = [ 'audio_url' => 'https://example.com/audio.mp3', 'language' => 'en', 'translate' => true, 'transcription_format' => 'srt', 'word_timestamps' => true ]; $ch = curl_init($url); curl_setopt($ch, CURLOPT_POST, true); curl_setopt($ch, CURLOPT_HTTPHEADER, $headers); curl_setopt($ch, CURLOPT_POSTFIELDS, $data); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); $response = curl_exec($ch); curl_close($ch); echo $response; // Option 2: File Upload $data = [ 'language' => 'en', 'translate' => false, 'transcription_format' => 'plain_text', 'word_timestamps' => true, 'audio_file' => new CURLFile('audio.mp3') ]; $ch = curl_init($url); curl_setopt($ch, CURLOPT_POST, true); curl_setopt($ch, CURLOPT_HTTPHEADER, $headers); curl_setopt($ch, CURLOPT_POSTFIELDS, $data); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); $response = curl_exec($ch); curl_close($ch); echo $response; - lang: Go source: "package main\n\nimport (\n\t\"bytes\"\n\t\"fmt\"\n\t\"io\"\n\t\"mime/multipart\"\n\t\"net/http\"\n\t\"os\"\n\t\"strings\"\n)\n\nfunc main() {\n\turl := \"https://api.musicgpt.com/api/public/v1/audio_transcribe\"\n\tapiKey := \"<<>>\"\n\n\t// Option 1: URL\n\tpayload := \"audio_url=https://example.com/audio.mp3&language=en&translate=true&transcription_format=srt&word_timestamps=true\"\n\treq, _ := http.NewRequest(\"POST\", url, strings.NewReader(payload))\n\treq.Header.Add(\"Authorization\", apiKey)\n\tres, _ := http.DefaultClient.Do(req)\n\tdefer res.Body.Close()\n\tbody, _ := io.ReadAll(res.Body)\n\tfmt.Println(string(body))\n\n\t// Option 2: File Upload\n\tfile, _ := os.Open(\"audio.mp3\")\n\tdefer file.Close()\n\tbodyBuf := &bytes.Buffer{}\n\twriter := multipart.NewWriter(bodyBuf)\n\twriter.WriteField(\"language\", \"en\")\n\twriter.WriteField(\"translate\", \"false\")\n\twriter.WriteField(\"transcription_format\", \"plain_text\")\n\twriter.WriteField(\"word_timestamps\", \"true\")\n\tpart, _ := writer.CreateFormFile(\"audio_file\", \"audio.mp3\")\n\tio.Copy(part, file)\n\twriter.Close()\n\n\treq, _ = http.NewRequest(\"POST\", url, bodyBuf)\n\treq.Header.Add(\"Authorization\", apiKey)\n\treq.Header.Add(\"Content-Type\", writer.FormDataContentType())\n\tres, _ = http.DefaultClient.Do(req)\n\tdefer res.Body.Close()\n\tbody, _ = io.ReadAll(res.Body)\n\tfmt.Println(string(body))\n}" - lang: Java source: // Java example omitted for brevity. Request if needed. components: securitySchemes: ApiKeyAuth: type: apiKey in: header name: Authorization ````