Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Deepgram

Browse Deepgram projects and transcribe publicly accessible audio or video.

Connectors

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

Connector
Authentication

Deepgram

API Key

Deepgram

Connect to Deepgram to browse projects and transcribe public audio or video URLs.

Set up in Deepgram

  1. Prepare the Deepgram account or service that the workflow will access. Grant access to the required resources and operations.

  2. API Key: A Deepgram API key. Create one in the Deepgram Console under API Keys and grant it access to the projects and transcription operations you need.

Set up in StackAI

  1. Open Settings → Connections, add a connection, and select Deepgram.

  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

A Deepgram API key. Create one in the Deepgram Console under API Keys and grant it access to the projects and transcription operations you need. Provider instructions.

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 Deepgram 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

List Projects

List the Deepgram projects available to the connected API key.

Inputs

No input fields are required in this catalog entry.

Outputs

Field
Type
Description

Projects

object_array

The accessible Deepgram projects.

Get Project

Get the name and Model Improvement Program setting for one Deepgram project.

Inputs

Field
Type
Required
Description

Project

select (string)

Yes

The Deepgram project to retrieve. Options load from the selected connection.

Outputs

Field
Type
Description

Project ID

string

The project's unique id.

Name

string

The project's display name.

Model Improvement Opt-out

boolean

Whether the project opts out of Deepgram's Model Improvement Program.

Get Project Balances

List the outstanding balances for one Deepgram project.

Inputs

Field
Type
Required
Description

Project

select (string)

Yes

The Deepgram project whose balances should be retrieved. Options load from the selected connection.

Outputs

Field
Type
Description

Balances

object_array

The project's outstanding balances.

Transcribe URL

Transcribe a publicly accessible audio or video URL with Deepgram.

Inputs

Field
Type
Required
Description

Audio or Video URL

string

Yes

A public URL that Deepgram can download and transcribe.

Model

select (string)

No

The Deepgram speech model to use. Available values: Nova-3, Nova-2. Default: nova-3.

Language

string

No

The primary spoken language in the recording. Default: en.

Smart Formatting

boolean

No

Format dates, times, numbers, and punctuation for readability. Default: true.

Punctuation

boolean

No

Add punctuation and capitalization to the transcript. Default: true.

Identify Speakers

boolean

No

Identify speaker changes and return speaker-labeled utterances. Default: false.

Separate Audio Channels

boolean

No

Transcribe each audio channel independently. Default: false.

Outputs

Field
Type
Description

Transcript

textarea

The primary transcription text.

Request ID

string

Deepgram's id for the transcription request.

Duration

number

The recording duration in seconds.

Confidence

number

Deepgram's confidence in the primary transcript.

Detected Language

string

The language Deepgram reports for the first channel.

Channels

object_array

The primary transcript and confidence for each audio channel.

Speaker Utterances

object_array

Speaker-labeled transcript segments when speaker identification is enabled.

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.

Last updated

Was this helpful?