> 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/speechmatics.md).

# Speechmatics

Submit batch audio transcription jobs and retrieve statuses and transcripts.

## Connectors

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

| Connector    | Authentication |
| ------------ | -------------- |
| Speechmatics | API Key        |

### Speechmatics

Connect to Speechmatics to manage batch transcription jobs.

#### Set up in Speechmatics

1. Prepare the Speechmatics account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create a project-scoped API key in the Speechmatics Portal under Projects > API keys, then paste it here.
3. **Batch Region:** Region used to create and retrieve jobs: eu1, us1, or au1. eu2 and us2 require an enterprise agreement.

#### Set up in StackAI

1. Open **Settings → Connections**, add a connection, and select **Speechmatics**.
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                      | Create a project-scoped API key in the Speechmatics Portal under Projects > API keys, then paste it here. [Provider instructions](https://portal.speechmatics.com/settings/api-keys). |
| Batch Region  | Optional / as applicable | Region used to create and retrieve jobs: eu1, us1, or au1. eu2 and us2 require an enterprise agreement.                                                                               |

### 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 **Speechmatics** 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

### Submit Transcription Job

Submit remote audio or video for batch transcription.

#### Inputs

| Field               | Type            | Required | Description                                                                                                                   |
| ------------------- | --------------- | -------- | ----------------------------------------------------------------------------------------------------------------------------- |
| Audio URL           | secret          | Yes      | Public or signed URL of the audio or video to transcribe. Stored as a secret because a signed URL grants access to the media. |
| Language            | string          | No       | Language code expected in the recording. Default: en.                                                                         |
| Model               | select (string) | No       | Recognition model used for the job. Available values: Standard, Enhanced, Melia 1. Default: standard.                         |
| Speaker Separation  | select (string) | No       | How speakers or audio channels should be labeled. Available values: None, Speakers, Audio Channels. Default: none.            |
| Format Entities     | boolean         | No       | Recognize formatted entities such as dates and numbers. Default: false.                                                       |
| Remove Disfluencies | boolean         | No       | Remove fillers and other detected disfluencies. Default: false.                                                               |
| Job Title           | string          | No       | Optional title used to identify the job.                                                                                      |
| External Reference  | string          | No       | Optional identifier from another system.                                                                                      |

#### Outputs

| Field     | Type    | Description                            |
| --------- | ------- | -------------------------------------- |
| Job ID    | string  | ID of the submitted transcription job. |
| Submitted | boolean | Whether Speechmatics accepted the job. |

### Get Job Status

Get the current status of a transcription job.

#### Inputs

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

#### Outputs

| Field | Type   | Description                                   |
| ----- | ------ | --------------------------------------------- |
| Job   | object | Current transcription job details and status. |

### Get Transcript

Retrieve the transcript for a completed job.

#### Inputs

| Field         | Type            | Required | Description                                                                                                                |
| ------------- | --------------- | -------- | -------------------------------------------------------------------------------------------------------------------------- |
| Job           | select (string) | Yes      | Completed transcription job to retrieve. Options load from the selected connection.                                        |
| Output Format | select (string) | No       | Transcript representation to retrieve. Available values: Plain Text, Speechmatics JSON v2, SubRip Subtitles. Default: txt. |

#### Outputs

| Field                 | Type   | Description                                   |
| --------------------- | ------ | --------------------------------------------- |
| Job ID                | string | ID of the transcribed job.                    |
| Format                | string | Transcript format returned.                   |
| Transcript Text       | string | Readable transcript or subtitle text.         |
| Structured Transcript | object | Structured JSON-v2 transcript when requested. |

### List Transcription Jobs

List recent Speechmatics transcription jobs.

#### Inputs

| Field | Type    | Required | Description                                           |
| ----- | ------- | -------- | ----------------------------------------------------- |
| Limit | integer | No       | Maximum number of recent jobs to return. Default: 25. |

#### Outputs

| Field | Type          | Description                             |
| ----- | ------------- | --------------------------------------- |
| Jobs  | object\_array | Recent transcription jobs and statuses. |
| Count | integer       | Number of jobs returned.                |

### Delete Transcription Job

Permanently delete a transcription job and transcript.

#### Inputs

| Field                      | Type            | Required | Description                                                                         |
| -------------------------- | --------------- | -------- | ----------------------------------------------------------------------------------- |
| Job                        | select (string) | Yes      | Transcription job to permanently delete. Options load from the selected connection. |
| Force Delete Running Job   | boolean         | No       | Terminate and delete the job if it is still running. Default: false.                |
| Confirm Permanent Deletion | boolean         | No       | Confirm permanent deletion of the selected job and transcript. Default: false.      |

#### Outputs

| Field       | Type    | Description                                           |
| ----------- | ------- | ----------------------------------------------------- |
| Deleted Job | object  | Speechmatics job returned by the deletion request.    |
| Deleted     | boolean | Whether Speechmatics accepted the permanent deletion. |

## 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/speechmatics.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.
