# Transcribe Audio

Turn completed episodes, custom URLs, or uploaded recordings into searchable transcripts that you can reuse across AutoContent.

## Before You Begin

* Add your API key in `Settings`; the transcription page requires authentication.
* Gather the audio source: an existing episode, a public HTTPS link, or a local audio file (MP3/WAV/M4A/FLAC, under 50 MB).
* Decide whether you want timestamps and speaker tags; the transcript viewer lets you toggle them later.

## Step 1: Open the Transcription Workspace

1. In the sidebar, go to `Tools -> Transcribe Audio` (`/tools/transcribe-audio`).
2. Confirm the warning banner shows your API key before submitting any jobs.

## Step 2: Pick an Audio Source

Choose one of the three source buttons at the top of the form:

* **Audio File** – Upload a local file. Validation blocks non-audio MIME types and files above 50 MB.
* **Your Episodes** – Browse completed podcasts pulled from `Content/List`, search by title, and select one.
* **Audio URL** – Paste a direct HTTPS link to an MP3, WAV, M4A, or FLAC file. The form checks common extensions for you.

## Step 3: Submit the Transcription Request

Select **Transcribe Audio**. The UI sends the appropriate payload and shows a confirmation banner with the `request_id`.

Behind the scenes the calls look like this:

```bash
# Upload a local file for transcription
curl -X POST "https://api.autocontentapi.com/content/GetTranscript" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "audioFile=@/path/to/interview.mp3"
```

```bash
# Transcribe an existing AutoContent episode
curl -X POST "https://api.autocontentapi.com/content/GetTranscript" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "episodeId": "episode-550e8400-e29b-41d4-a716-446655440000"
  }'
```

```bash
# Transcribe audio hosted online
curl -X POST "https://api.autocontentapi.com/content/GetTranscript" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audioUrl": "https://cdn.example.com/webinars/briefing.wav"
  }'
```

Successful requests return:

```json
{
  "request_id": "transcript-1234abcd",
  "status": 0
}
```

AutoContent queues the job and redirects you to review results in the right-hand transcripts list.

## Step 4: Review and Export Transcripts

* The **Transcripts** column lists every request with status, language (when detected), and errors if any occur.
* Select a transcript to open it in the modal viewer. Toggle timestamps, copy blocks of text, or download the raw segments.
* Use **Copy** to send the formatted transcript to your clipboard, or **Create** to jump directly into the podcast episode builder with that text preloaded.

## Step 5: Repurpose the Transcript

* Launch `Create Podcast Episode` from the transcript action to produce a narrated version of the conversation.
* Drop the transcript into your show notes, blogs, or X posts; the clipboard button formats it for instant reuse.
* Need to schedule audio based on these transcripts? Convert them into deep research or custom scripts, then follow [Create a Podcast Episode](/quick-start/podcasts/create-podcast-episode.md).

## Related Endpoints

* `POST /content/GetTranscript` – Start a transcription job (file, URL, or existing episode).
* `GET /content/Transcripts` – List submitted jobs and their statuses.
* `GET /content/Transcripts/{id}` – Retrieve transcript data programmatically.

## What's Next?

* Edit or polish the transcript before recording by starting [Create a Podcast Episode](/quick-start/podcasts/create-podcast-episode.md).
* Clone a custom host for the narration via [Clone a Voice](/quick-start/tools/clone-voice.md).
* Save supporting research notes with [Start Deep Research](/quick-start/deep-researches/start-deep-research.md).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.autocontentapi.com/quick-start/tools/transcribe-audio.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.