Eleven Labs
Eleven Labs is a text to speech provider that provides text to speech capabilities.
Connectors
Choose the connector that matches your authentication method. The options below use the names shown in StackAI.
Eleven Labs
API Key
Eleven Labs
Connect to Eleven Labs API for text-to-speech capabilities.
Set up in Eleven Labs
Sign in to Eleven Labs at https://elevenlabs.io.
Click your profile icon and select API Keys, then create a new API key and copy it.
Set up in StackAI
Open Settings → Connections, add a connection, and select Eleven Labs.
Enter the credentials and connection details in the fields below.
Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.
Connection fields
API Key
Yes
Your ElevenLabs API key. User, Voices and Models read access is required. The workspace usage analytics action additionally needs Workspace read access, so grant that too if you plan to use it.
Provider documentation: Setup reference.
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
Add the required Eleven Labs action to the workflow.
Select a connection when the action requests one.
Complete the required fields. Use the reference picker when a value comes from another workflow step.
Run the workflow and inspect the action’s output. Check the result before using it in a later step.
Actions
Text to Speech
Convert text to lifelike speech using Eleven Labs AI voices.
Inputs
Text
textarea
Yes
The text content to convert to speech.
Voice
select (string)
Yes
Select the voice to use. Options load from the selected connection.
Model
select (string)
Yes
Select the model to use. Options load from the selected connection.
Speed
percentage_slider
No
Controls the speed of the generated speech. Values below 1.0 slow down, above 1.0 speed up. Minimum: 0.7. Maximum: 1.2. Default: 1.0.
Stability
percentage_slider
No
Controls voice consistency. Lower = more expressive, Higher = more consistent. Minimum: 0.0. Maximum: 1.0. Default: 0.5.
Stability
select (string)
No
Controls voice consistency. Low = more expressive, High = more consistent. Available values: Low (0.0), Medium (0.5), High (1.0). Default: 0.5.
Similarity
percentage_slider
No
Boosts voice clarity and target speaker similarity. Very high values may cause artifacts. Minimum: 0.0. Maximum: 1.0. Default: 0.75.
Style Exaggeration
percentage_slider
No
Exaggerates speech style. Higher = more expressive but less stable. Minimum: 0.0. Maximum: 1.0. Default: 0.0.
Speaker Boost
boolean
No
Boosts voice clarity and similarity to the original voice. Default: true.
Outputs
File
object
The generated audio file metadata.
Signed URL
string
Temporary, pre-signed URL to download the audio.
Expiration Date
datetime
Timestamp for when the signed URL becomes invalid.
Get Usage Analytics
Read ElevenLabs workspace usage over a date range, broken down by product, model, voice, user or region.
Inputs
Date Range
select (string)
No
Pick a preset window, or choose 'custom' and set Start Date and End Date. Options load from the selected connection. Default: last_30_days.
Start Date
string
No
First day to include (YYYY-MM-DD). Needed for 'custom'.
End Date
string
No
Last day to include (YYYY-MM-DD). This day is included. Needed for 'custom'.
Group By
select (string)
No
Break the usage down by one or more dimensions. Leave empty for a single series over time. Options load from the selected connection. Default: product_type.
Interval
select (string)
No
Size of each time bucket. Choose a named width, or set Interval Seconds for an exact value. Options load from the selected connection.
Interval Seconds
integer
No
Exact bucket width in seconds (1-31536000). Overrides Interval when both are set. Minimum: 1. Maximum: 31536000.
Time Zone
string
No
IANA time zone the date range and the buckets are aligned to. Defaults to UTC.
Filter Column
select (string)
No
Narrow the report to specific values of one column, such as a single voice, user or region. Leave empty to report on everything. Options load from the selected connection.
Filter Operation
select (string)
No
How to compare the column against the values. Defaults to 'in'. Options load from the selected connection. Default: in.
Filter Values
string
No
Comma-separated values the filter column must match.
Outputs
Columns
array
The columns the query returned, with their types and units.
Rows
array
Result rows, each keyed by column name.
Totals
object
Each numeric column summed across every row.
Row Count
number
Number of rows returned.
Truncated
boolean
True when the query matched more than 10000 rows and only the first 10000 are returned.
Start Date
string
Inclusive start of the range covered (ISO 8601 UTC).
End Date
string
Exclusive end of the range covered (ISO 8601 UTC).
Get Subscription
Check the ElevenLabs plan and how much of this period's character quota is already used.
Inputs
No input fields are required in this catalog entry.
Outputs
Tier
string
The subscription plan this account is on.
Characters Used
number
Characters consumed in the current billing period.
Character Limit
number
Characters allowed in the current billing period.
Characters Remaining
number
Characters left before the quota is exhausted.
Percentage Used
number
Share of the quota consumed, as a percentage.
Resets At
string
When the character count resets (ISO 8601 UTC).
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?

