> ## Documentation Index
> Fetch the complete documentation index at: https://docs.plaud.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcription API

> Transcribe your user's conversation audio with Plaud's ASR and transcription models.

The Transcription API follows a polling model where you:

<Steps>
  <Step title="Submit Audio for Transcription">
    After uploading your audio to a publicly accessible URL — either via Plaud's [File Upload API](/plaud-embedded/file-api-overview) or your own storage — submit the URL to the Transcription API to kick off a transcription task.
  </Step>

  <Step title="Get Transcription Task">
    Use the `GET /transcription` endpoint to poll the Transcription API for the task status.
    On completion, the payload will include the transcribed data.
  </Step>
</Steps>

## Using the Transcription API

## Prerequisites

1. If you haven't done so, retrieve your `client_id` and `api_key` from the [developer portal](https://portal.plaud.ai/).

<Note>
  The `api_key` is NOT your `client_secret`. Navigate to App Settings > API Keys.
</Note>

<Frame>
  <img src="https://mintcdn.com/plaud/E1lTvtruOMzEP-O1/assets/generate-api-key.png?fit=max&auto=format&n=E1lTvtruOMzEP-O1&q=85&s=ab61c356775b848cff515f27703d9cfa" alt="generate api key" width="2216" height="1068" data-path="assets/generate-api-key.png" />
</Frame>

2. Have a publicly available download URL with the audio file you'd like to transcribe.

<Note>
  This `file_url` could be your cloud storage OR served through Plaud's [File Upload API](/plaud-embedded/file-api-overview) if you prefer Plaud to host your files.
</Note>

<Tip>
  Try the [Plaud Embedded API Playground](https://plaud-embedded-playground.vercel.app/) to see every step of the transcription process with your own client credentials.

  End-to-end, from **authentication** to **recording audio** to **uploading** to **transcription**.

  <Frame>
    <img src="https://mintcdn.com/plaud/3HJ-zGIl_uprusCq/assets/playground-ss.png?fit=max&auto=format&n=3HJ-zGIl_uprusCq&q=85&s=2eff3616a9b3d0cfe5f1bf4902d260b1" width="1760" height="858" data-path="assets/playground-ss.png" />
  </Frame>
</Tip>

### Submit File for Transcription

Submit a transcription task for Plaud Embedded's transcription and ASR models to process.

```http theme={"system"}
POST https://platform-us.plaud.ai/developer/api/open/partner/ai/transcriptions/
Content-Type: application/json
X-Client-Api-Key: [API_KEY]
X-Client-Id: [CLIENT_ID]

{
  "file_url": "<publicly accessible audio file URL>",
  "params": {
    "transcribe": { "language": "auto", "model": "plaud-fast-whisper" },
    "vad": { "decode_silence": false },
    "diarization": { "enabled": false, "return_embedding": false }
  }
}
```

```json theme={"system"}
{
  "transcription_id": "task_exec_xxx",
  "status": "PENDING",
  "data": {}
}
```

<Note>
  Recordings **exceeding 5 hours** should be broken into chunks and transcribed in parts.
</Note>

### Poll Transcription Task Until Completion

Check the status of your transcription task. On the `SUCCESS` status code, the transcript data will be included.

```http theme={"system"}
GET https://platform-us.plaud.ai/developer/api/open/partner/ai/transcriptions/[TRANSCRIPTION_ID]
X-Client-Api-Key: [API_KEY]
X-Client-Id: [CLIENT_ID]
```

```json expandable theme={"system"}
{
  "transcription_id": "task_exec_xxx",
  "status": "SUCCESS",
  "data": {
    "text": "Meeting started at 10am...",
    "language": "en",
    "duration": 1843,
    "segments": [
      {
        "start": 0,
        "end": 4.2,
        "text": "Meeting started at 10am.",
        "speaker": "Speaker 1"
      }
    ]
  }
}
```

<Note>
  Plaud's cloud services are hosted in the U.S. by default. If you're
  interested in multi-region hosting in Japan, Europe, and Singapore,
  please [reach out to our sales team](https://dev.plaud.ai/contact).
</Note>