> For the complete documentation index, see [llms.txt](https://morphic.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://morphic.com/docs/audio/transcription.md).

# Transcription

Transcription reads the speech in any audio or video file on Morphic and returns it as a subtitle document. Every line comes back with the timing it was spoken at, ready to caption a cut, pull quotes from an interview, or use as the base for a script.

Here's a quick tutorial on how to use Transcription on Morphic:

1. Open Canvas or Copilot on Morphic
2. Click the paper clip icon to attach the audio or video file you want transcribed. You can:

* Select on Canvas - pick a file already placed on your Canvas
* Select from Assets - pick from your Assets library
* Upload asset - upload a file from your device

3. Ask for the transcript, for example "Transcribe this." Add any extra direction in the same message: the spoken language, a translation, speaker labels, or word-level timings.
4. Hit the blue arrow. When the transcription finishes, the .srt file appears in the chat, ready to download.

#### What you can ask for

Write these into the same message as your request.

| Ask for this        | What you get                                                                 |
| ------------------- | ---------------------------------------------------------------------------- |
| Nothing extra       | The spoken language is detected automatically and returned as caption cues   |
| A specific language | A hint for noisy audio, or recordings that switch languages                  |
| A translation       | Each cue keeps the original line and adds the translation underneath it      |
| Speaker labels      | Each cue is prefixed with who is speaking                                    |
| Word-level timings  | One cue per word with its own start and end time, for karaoke-style captions |

#### What you get back

A single .srt file. Each cue carries a number, start and end timestamps down to the millisecond, and the line that was spoken.

```
1
00:00:00,000 --> 00:00:01,500
Hello world.

2
00:00:01,500 --> 00:00:03,000
Alice: Bonjour
Hi
```

#### Limits

| Input      | Details                                   |
| ---------- | ----------------------------------------- |
| Files      | One audio or video file per transcription |
| Audio size | Up to 500 MB                              |
| Video size | Up to 200 MB                              |

#### Tips for better results

* Feed it clean audio. Background music and crosstalk cost you accuracy.
* Name the language when the recording is quiet, or the speakers switch languages mid-sentence.
* Ask for speaker labels on anything with more than one voice. Interviews and panels are much easier to read when each cue is attributed.

That's how you use the Transcription feature on Morphic. Once you have the .srt file, you can download it as a script, or use it to caption the video itself. See [Subtitles](/docs/tools/subtitles.md).

***

If you have any trouble or have any questions, feel free to reach out. We're happy to help. Write to us at [**support@morphic.com**](mailto:support@morphic.com)**.**


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://morphic.com/docs/audio/transcription.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.