Actions2
Dub from Audio
AI-generatedSummary
Convert an audio file from a given URL into a dubbed audio output with optional language translation and voice adjustments, using the InfineTalk (Kie.ai) API.
Inputs
- Audio URL (required) — The publicly accessible URL of the source audio file to dub.
- Target Language — Optional ISO code for the target language to translate and dub the audio into.
- Speed — Multiplier for speech speed adjustment, ranging from 0.5 (half speed) to 2.0 (double speed), defaulting to 1 (normal speed).
- Pitch — Adjusts the voice pitch in semitones, from -12 to 12, where 0 is the original pitch.
- Volume — Multiplier for output volume from 0 (mute) to 2.0 (double volume), default is 1 (normal volume).
- Reply URL — Optional webhook URL to be called when the dubbing task completes asynchronously.
- Reply Ref — Optional custom reference string that will be included in the webhook callback for identifying the task.
- Wait for Completion — Whether to wait synchronously until the dubbing task completes before returning (default true). If false, the node returns immediately after task creation.
Output shape
a JSON object per input item describing the task creation result or final task result if wait for completion is enabled
If 'Wait for Completion' is true, the node polls the task status every 3 seconds up to 5 minutes to return the completed result; otherwise it returns immediately with task creation response containing a taskId. The returned data includes URLs to the dubbed audio and any translated content when available.
Examples
Example 1: Dub an English audio file at a URL into Spanish with faster speed and higher pitch, waiting synchronously for completion.
Set Audio URL to the source file link, Target Language to 'es', Speed to 1.5, Pitch to 3, and Wait for Completion to true.