Install the belt CLI skill: npx skills add belt-sh/cli
ElevenLabs Voice Changer
Transform any voice into a different voice via inference.sh CLI.
Quick Start
Requires inference.sh CLI (belt). Install instructions
belt login
# Transform voice
belt app run elevenlabs/voice-changer --input '{"audio": "https://recording.mp3", "voice": "aria"}'
Available Models
| Model |
ID |
Best For |
| Multilingual STS v2 |
eleven_multilingual_sts_v2 |
70+ languages (default) |
| English STS v2 |
eleven_english_sts_v2 |
English-optimized |
Voice Options
Same 22+ premium voices as ElevenLabs TTS:
| Voice |
Style |
george |
British, authoritative (default) |
aria |
American, conversational |
alice |
British, confident |
brian |
American, conversational |
charlie |
Australian, natural |
daniel |
British, commanding |
jessica |
American, expressive |
sarah |
American, friendly |
adam, bella, bill, callum, chris, eric, harry, laura, liam, lily, matilda, river, roger, will |
Various styles |
Examples
Basic Voice Transformation
# Change voice to British male
belt app run elevenlabs/voice-changer --input '{
"audio": "https://my-recording.mp3",
"voice": "george"
}'
# Change voice to American female
belt app run elevenlabs/voice-changer --input '{
"audio": "https://my-recording.mp3",
"voice": "aria"
}'
Choose Output Format
belt app run elevenlabs/voice-changer --input '{
"audio": "https://recording.mp3",
"voice": "daniel",
"output_format": "mp3_44100_192"
}'
English-Optimized Model
belt app run elevenlabs/voice-changer --input '{
"audio": "https://english-speech.mp3",
"voice": "brian",
"model": "eleven_english_sts_v2"
}'
Workflow: Voice-Over Replacement
# 1. Record yourself reading the script (any quality mic)
# 2. Transform to professional voice
belt app run elevenlabs/voice-changer --input '{
"audio": "https://my-rough-recording.mp3",
"voice": "george"
}' > professional.json
# 3. Add to video
belt app run infsh/video-audio-merger --input '{
"video_file": "video.mp4",
"audio_file": "<professional-audio-url>"
}'
Workflow: Character Voices
# Record one actor, create multiple characters
# Character 1: British narrator
belt app run elevenlabs/voice-changer --input '{
"audio": "https://actor-line1.mp3",
"voice": "george"
}' > char1.json
# Character 2: Young female
belt app run elevenlabs/voice-changer --input '{
"audio": "https://actor-line2.mp3",
"voice": "lily"
}' > char2.json
# Character 3: Casual male
belt app run elevenlabs/voice-changer --input '{
"audio": "https://actor-line3.mp3",
"voice": "charlie"
}' > char3.json
Use Cases
- Content Creation: Transform your voice for videos and podcasts
- Voice Acting: Create multiple characters from one performance
- Privacy: Anonymize voice in recordings
- Dubbing: Replace voices in video content
- Accessibility: Convert to preferred voice characteristics
- Prototyping: Test different voices before hiring talent
Related Skills
# ElevenLabs TTS (generate from text instead)
npx skills add inference-sh/skills@elevenlabs-tts
# ElevenLabs voice isolator (clean audio first)
npx skills add inference-sh/skills@elevenlabs-voice-isolator
# ElevenLabs dubbing (translate to other languages)
npx skills add inference-sh/skills@elevenlabs-dubbing
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
Browse all audio apps: belt app list --category audio
1---2name: elevenlabs-voice-changer-23description: ElevenLabs voice changer - transform any voice to a different voice while preserving speech content and emotion via inference.sh CLI. Models: eleven_multilingual_sts_v2 (70+ languages), eleven_english_sts_v2. Capabilities: speech-to-speech, voice transformation, accent change, voice disguise. Use for: content creation, voice acting, privacy, dubbing, character voices. Triggers: voice changer, speech to speech, voice transformation, change voice, voice swap, voice conversion, voice disguise, eleven labs voice changer, elevenlabs sts, transform voice, ai voice changer, voice modifier4---56> **Install the belt CLI skill:** `npx skills add belt-sh/cli`78# ElevenLabs Voice Changer910Transform any voice into a different voice via [inference.sh](https://inference.sh) CLI.11121314## Quick Start1516> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md)1718```bash19belt login2021# Transform voice22belt app run elevenlabs/voice-changer --input '{"audio": "https://recording.mp3", "voice": "aria"}'23```242526## Available Models2728| Model | ID | Best For |29|-------|----|----------|30| Multilingual STS v2 | `eleven_multilingual_sts_v2` | 70+ languages (default) |31| English STS v2 | `eleven_english_sts_v2` | English-optimized |3233## Voice Options3435Same 22+ premium voices as ElevenLabs TTS:3637| Voice | Style |38|-------|-------|39| `george` | British, authoritative (default) |40| `aria` | American, conversational |41| `alice` | British, confident |42| `brian` | American, conversational |43| `charlie` | Australian, natural |44| `daniel` | British, commanding |45| `jessica` | American, expressive |46| `sarah` | American, friendly |47| `adam`, `bella`, `bill`, `callum`, `chris`, `eric`, `harry`, `laura`, `liam`, `lily`, `matilda`, `river`, `roger`, `will` | Various styles |4849## Examples5051### Basic Voice Transformation5253```bash54# Change voice to British male55belt app run elevenlabs/voice-changer --input '{56 "audio": "https://my-recording.mp3",57 "voice": "george"58}'5960# Change voice to American female61belt app run elevenlabs/voice-changer --input '{62 "audio": "https://my-recording.mp3",63 "voice": "aria"64}'65```6667### Choose Output Format6869```bash70belt app run elevenlabs/voice-changer --input '{71 "audio": "https://recording.mp3",72 "voice": "daniel",73 "output_format": "mp3_44100_192"74}'75```7677### English-Optimized Model7879```bash80belt app run elevenlabs/voice-changer --input '{81 "audio": "https://english-speech.mp3",82 "voice": "brian",83 "model": "eleven_english_sts_v2"84}'85```8687## Workflow: Voice-Over Replacement8889```bash90# 1. Record yourself reading the script (any quality mic)91# 2. Transform to professional voice92belt app run elevenlabs/voice-changer --input '{93 "audio": "https://my-rough-recording.mp3",94 "voice": "george"95}' > professional.json9697# 3. Add to video98belt app run infsh/video-audio-merger --input '{99 "video_file": "video.mp4",100 "audio_file": "<professional-audio-url>"101}'102```103104## Workflow: Character Voices105106```bash107# Record one actor, create multiple characters108# Character 1: British narrator109belt app run elevenlabs/voice-changer --input '{110 "audio": "https://actor-line1.mp3",111 "voice": "george"112}' > char1.json113114# Character 2: Young female115belt app run elevenlabs/voice-changer --input '{116 "audio": "https://actor-line2.mp3",117 "voice": "lily"118}' > char2.json119120# Character 3: Casual male121belt app run elevenlabs/voice-changer --input '{122 "audio": "https://actor-line3.mp3",123 "voice": "charlie"124}' > char3.json125```126127## Use Cases128129- **Content Creation**: Transform your voice for videos and podcasts130- **Voice Acting**: Create multiple characters from one performance131- **Privacy**: Anonymize voice in recordings132- **Dubbing**: Replace voices in video content133- **Accessibility**: Convert to preferred voice characteristics134- **Prototyping**: Test different voices before hiring talent135136## Related Skills137138```bash139# ElevenLabs TTS (generate from text instead)140npx skills add inference-sh/skills@elevenlabs-tts141142# ElevenLabs voice isolator (clean audio first)143npx skills add inference-sh/skills@elevenlabs-voice-isolator144145# ElevenLabs dubbing (translate to other languages)146npx skills add inference-sh/skills@elevenlabs-dubbing147148# Full platform skill (all apps)149npx skills add inference-sh/skills@infsh-cli150```151152Browse all audio apps: `belt app list --category audio`
inference.sh