> ## Documentation Index
> Fetch the complete documentation index at: https://deepl-c950b784-docs-pipeline-20260911-145233.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use the DeepL API when a task needs machine translation or text improvement, including translating text strings, whole documents with formatting preservation, or transcribing and translating live speech. Preferred terminology and phrasing may be enforced using customizations (glossaries, style rules, and translation memories). Retrieve supported languages for each product from the `/v3/languages` endpoints.
> Read the machine-readable API surface instead of inferring request shapes from prose: the REST spec is at https://developers.deepl.com/api-reference/openapi.yaml (also served as openapi.json) and the Voice WebSocket protocol is at https://developers.deepl.com/api-reference/voice/voice.asyncapi.yaml. These docs also expose an MCP server at https://developers.deepl.com/mcp (Streamable HTTP, no authentication).
> Use https://api.deepl.com for Pro plans and https://api-free.deepl.com for the Free plan. Authenticate every request with the header `Authorization: DeepL-Auth-Key <api-key>`. Never fabricate an API key: ask the user for one, or point them at https://developers.deepl.com/docs/getting-started/quickstart.
> Errors use standard HTTP status codes with a JSON body containing a `message` field, plus a `code` field where available, and an `X-Trace-ID` response header that identifies the request in DeepL's logs. Log `X-Trace-ID` by default. Retry 429 and 5xx with exponential backoff. Do not retry 456, which means the account quota is exhausted, or 400, which means the request itself is invalid.

# Reference

> Status lifecycle, limits, supported audio formats, languages, and output formats for the Voice Translate Job API.

## Result Status Lifecycle

Each target result progresses through these statuses independently:

<Steps>
  <Step title="pending">Job created; source file not yet uploaded.</Step>
  <Step title="uploaded">Source file received; processing has not started.</Step>
  <Step title="processing">Translation in progress.</Step>
  <Step title="complete">Result is ready to download.</Step>
  <Step title="downloaded">Result has been downloaded; assets marked for deletion.</Step>
</Steps>

A target can transition to `failed` from any non-terminal state. When a target fails, the `error` field contains a description of the failure.

## Limits

| **Limit**                                             |                               **Value** |
| :---------------------------------------------------- | --------------------------------------: |
| Maximum file size                                     |              1 GB (1,073,741,824 bytes) |
| Maximum source duration                               |                                 3 hours |
| Time to upload after job creation                     |                               5 minutes |
| Time to download results after upload                 |                                  1 hour |
| Maximum concurrent jobs per customer                  |                                      10 |
| Maximum concurrent jobs per customer (files > 100 MB) |                                       2 |
| Maximum targets per job                               | No limit (constrained by storage quota) |

After all results are downloaded or the job expires, the job is deleted and returns `404`. Usage is billed based on the duration of the source audio.

Source audio over 3 hours is rejected, even if the file is under 1 GB. For longer recordings, split the source into chunks and submit each as its own job.

## Supported Source Audio Formats

* `audio/mpeg`
* `audio/wav`
* `audio/ogg`
* `audio/flac`
* `audio/mp4`
* `audio/webm`

## Supported Languages

Source and target languages match the [real-time Voice API](/docs/voice/supported-voice-languages). `source_language` is optional; if omitted, the language is detected automatically.

## Supported Output Formats

Each target specifies a `type` for the desired output format.

| **Type**                                       | **Description**                           |
| :--------------------------------------------- | :---------------------------------------- |
| `text/plain`                                   | Plain text transcript                     |
| `application/x-subrip`                         | SRT subtitle file with original timecodes |
| `audio/opus`                                   | Opus audio                                |
| `audio/flac`                                   | FLAC audio                                |
| `audio/pcm;encoding=s16le;rate=16000`          | PCM 16-bit signed LE, 16 kHz              |
| `audio/pcm;encoding=s16le;rate=24000`          | PCM 16-bit signed LE, 24 kHz              |
| `audio/pcm;encoding=ulaw;rate=8000`            | PCM u-law, 8 kHz                          |
| `audio/pcm;encoding=alaw;rate=8000`            | PCM A-law, 8 kHz                          |
| `audio/x-matroska;codecs=aac`                  | Matroska with AAC                         |
| `audio/x-matroska;codecs=flac`                 | Matroska with FLAC                        |
| `audio/x-matroska;codecs=opus`                 | Matroska with Opus                        |
| `audio/x-matroska;codecs=pcm_s16le;rate=16000` | Matroska with PCM 16 kHz                  |
| `audio/x-matroska;codecs=pcm_s16le;rate=24000` | Matroska with PCM 24 kHz                  |
| `video/mp2t;codecs=aac`                        | MPEG-TS with AAC                          |
| `video/mp2t;codecs=opus`                       | MPEG-TS with Opus                         |
| `audio/ogg;codecs=flac`                        | Ogg with FLAC                             |
| `audio/ogg;codecs=opus`                        | Ogg with Opus                             |
| `audio/webm;codecs=opus`                       | WebM with Opus                            |