mcpField
E
elevenlabs-voice-isolator

elevenlabs-voice-isolator

github.com/inference-shCreative & media789754 installsUpdated 2w ago
Repository

About elevenlabs-voice-isolator

A belt CLI skill that removes background noise and isolates voices from audio using inference.sh. It accepts several common audio formats and can be used to prepare recordings for transcription or voice transformation.

Key features

  1. 01Isolate voices from audio
  2. 02Remove noise, music, echo, and reverb
  3. 03Support WAV, MP3, FLAC, OGG, and AAC
  4. 04Process files up to one hour

Use cases

  1. 01Clean podcast or meeting recordings
  2. 02Reduce ambient noise in interviews
  3. 03Extract vocals from music
  4. 04Prepare audio for transcription or voice cloning

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/inference-sh/skills --skill elevenlabs-voice-isolator

After installing, type/elevenlabs-voice-isolatorin Claude Code to confirm it loaded.

Details

From the project README

Install the belt CLI skill: npx skills add belt-sh/cli

ElevenLabs Voice Isolator

Remove background noise and isolate voices from audio via inference.sh CLI.

Voice Isolator

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Isolate voice from noisy audio
belt app run elevenlabs/voice-isolator --input '{"audio": "https://noisy-recording.mp3"}'

Supported Formats

FormatMax SizeMax Duration
WAV500MB1 hour
MP3500MB1 hour
FLAC500MB1 hour
OGG500MB1 hour
AAC500MB1 hour

Examples

Clean Up a Recording
# Remove background noise from a podcast recording
belt app run elevenlabs/voice-isolator --input '{"audio": "https://noisy-podcast.mp3"}'
Clean Interview Audio
# Isolate speaker from café background noise
belt app run elevenlabs/voice-isolator --input '{"audio": "https://cafe-interview.mp3"}'
Extract Vocals from Music
# Separate vocals from instrumental
belt app run elevenlabs/voice-isolator --input '{"audio": "https://song.mp3"}'

What It Removes

  • Ambient/environmental noise
  • Background music
  • Reverb and echo
  • Wind noise
  • Traffic and crowd noise
  • Electrical hum/buzz
  • Other non-voice sounds

Workflow: Clean → Transcribe

# 1. Isolate voice from noisy recording
belt app run elevenlabs/voice-isolator --input '{
  "audio": "https://noisy-meeting.mp3"
}' > cleaned.json

# 2. Transcribe the clean audio
belt app run elevenlabs/stt --input '{
  "audio": "<cleaned-audio-url>",
  "diarize": true
}'

Workflow: Clean → Voice Change

# 1. Clean up the audio
belt app run elevenlabs/voice-isolator --input '{
  "audio": "https://raw-recording.mp3"
}' > cleaned.json

# 2. Transform the voice
belt app run elevenlabs/voice-changer --input '{
  "audio": "<cleaned-audio-url>",
  "voice": "george"
}'

Workflow: Clean → Add to Video

# 1. Clean the voiceover
belt app run elevenlabs/voice-isolator --input '{
  "audio": "https://raw-voiceover.mp3"
}' > cleaned.json

# 2. Merge with video
belt app run infsh/video-audio-merger --input '{
  "video_file": "video.mp4",
  "audio_file": "<cleaned-audio-url>"
}'

Use Cases

  • Podcasts: Clean up recordings with background noise
  • Interviews: Remove café/office ambient sounds
  • Music: Extract vocals for remixes or karaoke
  • Video Production: Clean dialogue audio
  • Archival: Restore old or degraded recordings
  • Meetings: Improve recording clarity
  • Voice Cloning Prep: Clean source audio for better cloning results

Related Skills

# ElevenLabs voice changer (transform voice after cleaning)
npx skills add inference-sh/skills@elevenlabs-voice-changer

# ElevenLabs STT (transcribe clean audio)
npx skills add inference-sh/skills@elevenlabs-stt

# ElevenLabs TTS (generate clean speech from text)
npx skills add inference-sh/skills@elevenlabs-tts

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

Browse all audio apps: belt app list --category audio

Comments

Markdown supported