Silence Removal and Audio Cleanup

Remove dead air, pauses, and filler words from video and audio timelines with automatic music ducking.

Remove dead air, pauses, and filler words from video and audio timelines with automatic music ducking.

Setup

This skill calls the Levea (livecore.ai) editing service, which requires a Levea account and API key.

1. Sign up and generate an API key at https://livecore.ai/?openclaw=1&utm_source=clawhub&utm_medium=skill&utm_campaign=silence-removal-audio-cleanup
2. Provide the key to the tool you use:
   • OpenClaw plugin openclaw-ai-video-editor (ClawHub): set apiKey in the plugin config.
   • MCP server levea-mcp-server (npm): set LEVEA_API_KEY in the MCP server config. LEVEA_API_URL is optional and defaults to https://api.livecore.ai.
3. Describe the edit you want in plain language; the tool returns a project ID and, after export, an MP4 URL.

When to use

• Removing silent pauses and dead air from spoken-word recordings.
• Trimming filler words and tightening conversational pacing.
• Balancing dialogue loudness and ducking background music under speech.

Tool interface

Use the registered ai-video-editor (OpenClaw plugin) or autonomous_edit (MCP server) tool to run edits against a project timeline.

Tool parameters

• prompt (string, required): Description of the video edit to perform, in the user's own words.
• project_id (string, optional): Project identifier returned by a prior call; reuse it for every follow-up edit on the same video.
• video_url (string, optional): Public source video URL when starting a new project.
• assets (array, optional): Input media (video, image, audio) as public HTTP/HTTPS URLs.
• scene (object, optional): Existing scene/timeline state to continue editing (advanced).
• captionTemplatePreset (string, optional): Caption template id to apply: a builtin slug (e.g. hormozi, viral-pop, karaoke) or a saved template id. With the MCP server, list_caption_templates lists the exact ids; elsewhere, name the look in the prompt.
• captionTemplateMode (string, optional): How to apply captionTemplatePreset: one of add, recreate, style, translate, clear, remove_fillers.
• requirePlanApproval (boolean, optional): When true, pause after planning and return workingMemory for the user to approve.
• workingMemory (object, optional): State returned by a paused plan-approval call; send it back to resume.
• editedPlan (object, optional): The user's edited version of a plan returned by an approval pause.
• planDecision (string, optional): Set to "approve" to approve the plan from an approval pause; resend it with that response's workingMemory.
• attachedImages (array, optional): Reference image URLs for planning (style, branding).
• flaggedIssues (array, optional): Specific problems the user flagged that this run must fix.
• brandId (string, optional): Brand kit to apply to this call.
• projectBrandId (string, optional): Default brand kit for the project; persists across calls.
• core_only (boolean, optional): Return only rendering-essential scene fields (smaller responses).

Example tool input

json

{
  "prompt": "Remove silences longer than 0.5 seconds, cut filler words, and normalize dialogue audio to -14 LUFS.",
  "project_id": "project_example_01"
}

Capabilities

• Silence and pause detection with frame-accurate timeline trimming.
• Filler-word removal and breath attenuation.
• Licensed library music fitted to the video length, sound effects on cuts, and sidechain ducking under dialogue.
• Broadcast loudness normalization and vocal clarity EQ.

Response fields

• success (boolean): True when the edit and verification passed.
• status (string): One of completed, waiting, awaiting_approval, or failed.
• projectId (string): Active project identifier for subsequent edits.
• projectRevision (number): Committed project revision number.
• videoUrl (string, optional): Rendered MP4 download URL when export completes.
• verificationReport (object): status is verified, rejected, unverified, or not_applicable, with each failed check and what repair tried.
• qualityNotes (array, optional): Advisory notes about the result.
• jobId (string, optional): Async render job identifier for status polling via check_job_status.