Skip to main content
POST
cURL
Use POST /runwayml/v1/voice_isolation to separate speech from background audio. Use the model ID eleven_voice_isolation. Send your CometAPI API key with Bearer authentication and a JSON request body.

Provide source audio

The request requires model and audioUri. Set audioUri to an accessible HTTPS URL of the recording that contains the speech to isolate. Replace the example audio URL with your source file.

Retrieve the result

Save the returned id, then use Get a Runway task to retrieve task status. When status is SUCCEEDED, read the audio URLs in output. If the task fails, inspect failure and failureCode.

Authorizations

Authorization
string
header
required

Use your CometAPI API key.

Body

application/json

Request settings for eleven_voice_isolation.

model
enum<string>
required

Model ID for this request.

Available options:
eleven_voice_isolation
Allowed value: "eleven_voice_isolation"
audioUri
required

Audio input as an accessible HTTPS URL or base64 data URI.

Required string length: 13 - 2048
Pattern: ^https:\/\/.*

Response

Task created. Save the returned id to retrieve task status.

id
string
required

Task ID for GET /runwayml/v1/tasks/{id}.

status
string

Task state, when returned.

createdAt
string<date-time>

Task submission timestamp, when returned.

output
string<uri>[]

Result URLs, when returned.

failure
string

Failure explanation, when returned.

failureCode
string

Machine-readable failure code, when returned.

estimatedCost
object

Task estimate metadata, when returned.

cost
object

Task cost metadata, when returned.

Last modified on September 21, 2026