Audio
Isolate a Runway voice
Separate speech from background audio with the Runway API.
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 requiresmodel 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 returnedid, 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
Use your CometAPI API key.
Body
application/json
Request settings for eleven_voice_isolation.
Response
Task created. Save the returned id to retrieve task status.
Task ID for GET /runwayml/v1/tasks/{id}.
Task state, when returned.
Task submission timestamp, when returned.
Result URLs, when returned.
Failure explanation, when returned.
Machine-readable failure code, when returned.
Task estimate metadata, when returned.
Task cost metadata, when returned.
Last modified on September 21, 2026