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

# Gladia

Transcribe pre-recorded audio and video, with diarization, summarization, and translation.

### Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector | Authentication |
| --------- | -------------- |
| Gladia    | API key        |

#### Gladia

Connect Gladia with an account API key to transcribe audio and video.

**Set up in Gladia**

1. Prepare the Gladia account or service that the workflow will access. Grant access to the required resources and operations.
2. **API key:** Find your personal API key on app.gladia.io under API keys.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Gladia**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                               |
| ------------- | -------- | ----------------------------------------------------------------------------------------------------------- |
| API key       | Yes      | Find your personal API key on app.gladia.io under API keys. [Provider instructions](https://app.gladia.io). |

#### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

### Use an action

1. Add the required **Gladia** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

### Actions

#### Upload audio file

Copy a public audio or video file into Gladia storage and return its Gladia file URL, duration, size, and channel count. Gladia downloads the file from the URL you give.

**Inputs**

| Field              | Type   | Required | Description                                                                           |
| ------------------ | ------ | -------- | ------------------------------------------------------------------------------------- |
| Audio or video URL | string | Yes      | A public or presigned HTTPS link to the audio or video file that Gladia can download. |

**Outputs**

| Field              | Type    | Description                                              |
| ------------------ | ------- | -------------------------------------------------------- |
| Gladia audio URL   | string  | The Gladia-hosted file URL to use with Transcribe audio. |
| File ID            | string  | Gladia id of the uploaded file.                          |
| File name          | string  | The detected file name.                                  |
| Duration (seconds) | number  | Length of the audio in seconds.                          |
| Size (bytes)       | integer | File size in bytes.                                      |
| Channels           | integer | Number of audio channels.                                |

#### Transcribe audio

Start a transcription of an audio or video file from a URL. The job runs in the background; use Get transcription result with the returned ID to read the transcript. Each run counts against your Gladia plan's hours and concurrency. Blank language means Gladia detects it.

**Inputs**

| Field              | Type                      | Required | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
| ------------------ | ------------------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Audio or video URL | string                    | Yes      | The Gladia file URL from Upload audio file, or a public or presigned HTTPS link to the file.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
| Spoken language    | select (string)           | No       | Language code of the audio, such as en or fr. Leave blank to let Gladia detect it. Available values: Afrikaans (af), Amharic (am), Arabic (ar), Assamese (as), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Tibetan (bo), Breton (br), Bosnian (bs), Catalan (ca), Czech (cs), Welsh (cy), Danish (da), German (de), Greek (el), English (en), Spanish (es), Estonian (et), Basque (eu), Persian (fa), Finnish (fi), Faroese (fo), French (fr), Galician (gl), Gujarati (gu), Hausa (ha), Hawaiian (haw), Hebrew (he), Hindi (hi), Croatian (hr), Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Icelandic (is), Italian (it), Japanese (ja), Javanese (jw), Georgian (ka), Kazakh (kk), Khmer (km), Kannada (kn), Korean (ko), Latin (la), Luxembourgish (lb), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Maori (mi), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Maltese (mt), Burmese (my), Nepali (ne), Dutch (nl), Norwegian Nynorsk (nn), Norwegian (no), Occitan (oc), Punjabi (pa), Polish (pl), Pashto (ps), Portuguese (pt), Romanian (ro), Russian (ru), Sanskrit (sa), Sindhi (sd), Sinhala (si), Slovak (sk), Slovenian (sl), Shona (sn), Somali (so), Albanian (sq), Serbian (sr), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Telugu (te), Tajik (tg), Thai (th), Turkmen (tk), Tagalog (tl), Turkish (tr), Tatar (tt), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Yiddish (yi), Yoruba (yo), Chinese (zh).                                           |
| Multiple languages | boolean                   | No       | Turn on when speakers change language during the recording. Default: false.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
| Identify speakers  | boolean                   | No       | Label each part of the transcript with its speaker. Default: false.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
| Number of speakers | integer                   | No       | Exact number of speakers, if you know it. Used only when Identify speakers is on.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
| Summarize          | boolean                   | No       | Also create a short summary of the transcript. Default: false.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| Translate to       | multiple\_select (string) | No       | Comma-separated language codes to translate the transcript into, such as fr, de. Leave blank for no translation. Available values: Afrikaans (af), Amharic (am), Arabic (ar), Assamese (as), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Tibetan (bo), Breton (br), Bosnian (bs), Catalan (ca), Czech (cs), Welsh (cy), Danish (da), German (de), Greek (el), English (en), Spanish (es), Estonian (et), Basque (eu), Persian (fa), Finnish (fi), Faroese (fo), French (fr), Galician (gl), Gujarati (gu), Hausa (ha), Hawaiian (haw), Hebrew (he), Hindi (hi), Croatian (hr), Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Icelandic (is), Italian (it), Japanese (ja), Javanese (jw), Georgian (ka), Kazakh (kk), Khmer (km), Kannada (kn), Korean (ko), Latin (la), Luxembourgish (lb), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Maori (mi), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Maltese (mt), Burmese (my), Nepali (ne), Dutch (nl), Norwegian Nynorsk (nn), Norwegian (no), Occitan (oc), Punjabi (pa), Polish (pl), Pashto (ps), Portuguese (pt), Romanian (ro), Russian (ru), Sanskrit (sa), Sindhi (sd), Sinhala (si), Slovak (sk), Slovenian (sl), Shona (sn), Somali (so), Albanian (sq), Serbian (sr), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Telugu (te), Tajik (tg), Thai (th), Turkmen (tk), Tagalog (tl), Turkish (tr), Tatar (tt), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Wolof (wo), Yiddish (yi), Yoruba (yo), Chinese (zh). |

**Outputs**

| Field            | Type   | Description                      |
| ---------------- | ------ | -------------------------------- |
| Transcription ID | string | ID of the new transcription job. |
| Status           | string | Initial job status.              |

#### List transcriptions

List your Gladia pre-recorded transcription jobs, newest first as Gladia returns them, optionally filtered by status and date range.

**Inputs**

| Field           | Type            | Required | Description                                                                                           |
| --------------- | --------------- | -------- | ----------------------------------------------------------------------------------------------------- |
| Status          | select (string) | No       | Only list jobs in this state. Leave blank for all. Available values: Queued, Processing, Done, Error. |
| After           | datetime        | No       | Only jobs created after this date and time.                                                           |
| Before          | datetime        | No       | Only jobs created before this date and time.                                                          |
| Maximum results | integer         | No       | How many jobs to return (1 to 100). Default: 20.                                                      |
| Offset          | integer         | No       | Number of jobs to skip. Use the Next offset from an earlier run to read the next page. Default: 0.    |

**Outputs**

| Field          | Type          | Description                                             |
| -------------- | ------------- | ------------------------------------------------------- |
| Transcriptions | object\_array | The jobs on this page.                                  |
| Next offset    | integer       | Offset for the next page, empty when there are no more. |

#### Get transcription result

Get the status of a transcription job and, when it is done, the full transcript, detected languages, speaker utterances, summary, and translations.

**Inputs**

| Field         | Type            | Required | Description                                                               |
| ------------- | --------------- | -------- | ------------------------------------------------------------------------- |
| Transcription | select (string) | Yes      | The transcription job to read. Options load from the selected connection. |

**Outputs**

| Field              | Type          | Description                                  |
| ------------------ | ------------- | -------------------------------------------- |
| Transcription ID   | string        | Job id.                                      |
| Status             | string        | queued, processing, done, or error.          |
| Transcript         | string        | Full transcript text when done.              |
| Languages          | string\_array | Detected languages.                          |
| Utterances         | object\_array | Transcript segments with times and speakers. |
| Summary            | string        | Summary, if requested.                       |
| Translations       | object\_array | Translated transcripts, if requested.        |
| Duration (seconds) | number        | Audio length.                                |
| Created            | string        | When the job was created.                    |
| Completed          | string        | When the job finished.                       |
| Error code         | integer       | HTTP-style error code if the job failed.     |

#### Delete transcription

Permanently delete a finished transcription job and its data from Gladia. This cannot be undone. Jobs still queued or processing cannot be deleted.

**Inputs**

| Field         | Type            | Required | Description                                                                 |
| ------------- | --------------- | -------- | --------------------------------------------------------------------------- |
| Transcription | select (string) | Yes      | The transcription job to delete. Options load from the selected connection. |

**Outputs**

| Field            | Type    | Description                           |
| ---------------- | ------- | ------------------------------------- |
| Transcription ID | string  | The deleted job id.                   |
| Deleted          | boolean | True when Gladia accepted the delete. |

### Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/gladia.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
