> 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/assemblyai.md).

# AssemblyAI

Transcribe reachable audio or video and manage transcript results.

### Connectors

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

| Connector  | Authentication |
| ---------- | -------------- |
| AssemblyAI | API Key        |

#### AssemblyAI

Connect to AssemblyAI to transcribe audio and manage transcript results.

**Set up in AssemblyAI**

1. Prepare the AssemblyAI account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create an API key in the AssemblyAI dashboard for the project to use.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **AssemblyAI**.
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 an API key in the AssemblyAI dashboard for the project to use. [Provider instructions](https://www.assemblyai.com/docs/account-management). |
| Region        | Optional / as applicable | Choose the US or EU AssemblyAI region where this project's API key is used.                                                                        |

#### 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 **AssemblyAI** 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

#### Transcribe audio file

Start an asynchronous transcription from a public or presigned HTTPS audio or video file URL.

**Inputs**

| Field                   | Type            | Required | Description                                                                                                                                                                          |
| ----------------------- | --------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Media file URL          | string          | Yes      | A public or presigned HTTPS URL for an audio or video file that AssemblyAI can fetch.                                                                                                |
| Speech model API value  | select (string) | No       | Choose an AssemblyAI speech model API value, or leave blank to use the provider's model routing. Available values: Universal-3.5 Pro (universal-3-5-pro), Universal-2 (universal-2). |
| Spoken language code    | string          | No       | AssemblyAI language\_code for the dominant spoken language, such as en\_us. Leave blank to use AssemblyAI's default, en\_us (US English).                                            |
| Identify speakers       | boolean         | No       | Separate the transcript by speaker when the recording contains a conversation. Default: false.                                                                                       |
| Separate audio channels | boolean         | No       | Transcribe each channel separately for multichannel recordings. Default: false.                                                                                                      |
| Filter profanity        | boolean         | No       | Replace profanity in the returned transcript text. Default: false.                                                                                                                   |

**Outputs**

| Field                     | Type   | Description                                                                                                           |
| ------------------------- | ------ | --------------------------------------------------------------------------------------------------------------------- |
| Transcript ID (UUID)      | string | The AssemblyAI transcript UUID created for this transcription job; reuse it with Get transcript or Delete transcript. |
| Initial transcript status | string | The AssemblyAI processing status returned when the job was created.                                                   |

#### Get transcript

Retrieve the current status and available results for one transcript.

**Inputs**

| Field                | Type            | Required | Description                                                                                  |
| -------------------- | --------------- | -------- | -------------------------------------------------------------------------------------------- |
| Transcript ID (UUID) | select (string) | Yes      | The exact AssemblyAI transcript UUID to retrieve. Options load from the selected connection. |

**Outputs**

| Field                       | Type          | Description                                                                                |
| --------------------------- | ------------- | ------------------------------------------------------------------------------------------ |
| Transcript ID (UUID)        | string        | The exact AssemblyAI transcript UUID; reuse it with Get transcript or Delete transcript.   |
| Transcript status           | string        | The current transcription status.                                                          |
| Transcript text             | textarea      | The completed transcript text, when available.                                             |
| Media duration (seconds)    | integer       | The media duration in seconds, when available.                                             |
| Transcript language code    | string        | The AssemblyAI language code (`language_code`) associated with the transcript.             |
| Transcript confidence score | number        | AssemblyAI's overall transcript confidence score from 0 to 1, when available.              |
| Utterances                  | object\_array | Speaker- or channel-separated transcript segments with millisecond timing, when available. |

#### List transcripts

List recent transcripts from newest to oldest with optional filters and a resumable cursor.

**Inputs**

| Field                    | Type            | Required | Description                                                                                                                                                                       |
| ------------------------ | --------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Maximum transcripts      | integer         | No       | The maximum number of transcript summaries to return. Default: 100.                                                                                                               |
| Transcript status filter | select (string) | No       | Return only transcripts with the selected exact AssemblyAI processing status. Available values: queued (waiting), processing (in progress), completed (finished), error (failed). |
| Transcript creation date | date            | No       | Return only transcripts whose AssemblyAI created\_on date is this YYYY-MM-DD calendar date.                                                                                       |
| Older-transcripts cursor | string          | No       | Pass the older-transcripts cursor returned by an earlier List transcripts call to continue toward older results.                                                                  |

**Outputs**

| Field                    | Type          | Description                                                                               |
| ------------------------ | ------------- | ----------------------------------------------------------------------------------------- |
| Transcript summaries     | object\_array | Structured transcript summaries with exact UUIDs, provider statuses, and timestamps.      |
| Transcript count         | integer       | The number of transcript summaries returned.                                              |
| Older-transcripts cursor | string        | Pass this full cursor to List transcripts to continue toward older results, when present. |

#### Delete transcript

Permanently delete a transcript and its retained AssemblyAI data.

**Inputs**

| Field                                      | Type            | Required | Description                                                                                                                                                                                                               |
| ------------------------------------------ | --------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Transcript ID (UUID) to permanently delete | select (string) | Yes      | Select the exact AssemblyAI transcript UUID to permanently delete. Verify the UUID and preserve any needed content first; this cannot be undone and there is no recovery path. Options load from the selected connection. |

**Outputs**

| Field                         | Type    | Description                                                                                       |
| ----------------------------- | ------- | ------------------------------------------------------------------------------------------------- |
| Transcript ID (UUID)          | string  | The exact AssemblyAI transcript UUID requested for deletion.                                      |
| Transcript absent             | boolean | Whether the transcript is confirmed absent after this action.                                     |
| Already absent before request | boolean | Whether AssemblyAI reported that no matching transcript existed when the delete request was made. |

### 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/assemblyai.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.
