Actions28
- Music Generation Actions
- Vocals Actions
- Persona Actions
- Lyrics Actions
- Vocal Separation Actions
- Audio Conversion Actions
- Style Boost Actions
- Cover Image Actions
- Task Details Actions
- Credit Actions
- File Upload Actions
Music Generation → Extend Music
AI-generatedSummary
Extend an existing music track by providing its Audio ID and optional parameters such as prompt, style, title, continuation timestamp, and whether the extension should be instrumental only. The operation uses an AI model to generate the extended segment and notifies via a callback URL upon completion.
Inputs
- Use Custom Parameters (required) — Enable to specify custom prompt, style, title, continuation time, and instrumental preference for the extension.
- Audio ID (required) — The audio ID of the specific track to extend.
- Callback URL (required) — A publicly accessible HTTPS URL to receive task completion notifications.
- Model (required) — Select the AI model version used for generation with options like V5, V4.5 Plus, etc.
- Prompt — Optional lyrics or text prompt guiding the extension; max length depends on model and custom parameter usage.
- Style — Optional music style or genre tags for the extension; max length depends on the model.
- Title — Optional title for the extended track; max length depends on the model.
- Continue At (seconds) — Timestamp in seconds from which to continue the extension.
- Instrumental — Flag to generate an instrumental-only extension without vocals.
- Negative Tags — Music styles or traits to exclude from the generated extension.
- Persona ID — Persona ID for custom style obtained from the Generate Persona operation.
- Persona Model — Type of persona to apply: Style Persona or Voice Persona (voice persona requires model V5).
- Style Weight — Floating point (0.00-1.00) indicating the style influence strength.
- Weirdness Constraint — Floating point (0.00-1.00) limiting creative deviation.
- Audio Weight — Floating point (0.00-1.00) determining input audio influence.
- Vocal Gender — Preferred vocal gender for the generated track, Male or Female.
Output shape
a single JSON object representing the API response confirming task initiation and containing task metadata
The operation returns immediately after task submission. The actual extended audio generation completes asynchronously, with task completion notified via the specified callback URL. Use the returned task metadata to track status or fetch results.