How to Use ElevenLabs Voice Changer Multilingual v2 in Muse Code
Use ElevenLabs Voice Changer Multilingual v2 to recast recorded dialogue while retaining its emotion and timing. It supports 29 languages, and ElevenLabs recommends it over ElevenLabs English Speech to Speech v2 even for English recordings.
Prompts to try with ElevenLabs Voice Changer Multilingual v2 in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use ElevenLabs Voice Changer Multilingual v2 to convert assets/audio/demo-take.wav into our chosen narrator voice, retaining the recorded delivery.
Use ElevenLabs Voice Changer Multilingual v2 on the recorded guard dialogue in assets/audio/guards, preserving each line's emotional emphasis.
Use ElevenLabs Voice Changer Multilingual v2 to compare lower and higher stability on the first 20 seconds of narration.wav. Save both for review.
Use ElevenLabs Voice Changer Multilingual v2 to recast the French tutorial recordings in this project, retaining their language and accent.
Use ElevenLabs Voice Changer Multilingual v2 on the demo narration. Divide it into chunks of five minutes or less and keep each input under 50 MB.
How to set up ElevenLabs Voice Changer Multilingual v2 in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run ElevenLabs Voice Changer Multilingual v2
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "elevenlabs", "model": "eleven_multilingual_sts_v2", "input": { "audio": "<audio>", "voice_id": "<voice_id>" } }'
Then paste one of the prompts above: Muse Code finds ElevenLabs Voice Changer Multilingual v2 on Spiral, shows the price and runs it.
ElevenLabs Voice Changer Multilingual v2 providers and prices
Spiral runs ElevenLabs Voice Changer Multilingual v2 through ElevenLabs. Open a card for today's price, with every fee included.
Settings you can ask for
ElevenLabs Voice Changer Multilingual v2 works from your audio. Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | 0 to 4294967295 | If specified, our system will make a best effort to sample deterministically. Must be integer between 0 and 4294967295. | |
| File format | pcm_s16le_16 or other | other | The format of input audio. Options are 'pcm_s16le_16' or 'other'. For |
| Output format | alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96 and 20 more | mp3_44100_128 | Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. |
| Remove background noise | on or off | off | If set, will remove the background noise from your audio input using our audio isolation model. |
Every API field of ElevenLabs Voice Changer (Multilingual) is on its tool page: open its card above.
What can you do with ElevenLabs Voice Changer Multilingual v2 in Muse Code?
Turn recorded project dialogue into character voices or recast a demo narration. An agent can organize short conversions and keep each result paired with its source recording.
Recast a video narration
Convert a recorded voiceover into another narrator's voice while retaining the delivery used for the edit.
Create game character dialogue
Act out short character lines, then convert the recordings while retaining their emotional emphasis.
Voice an animated scene
Record the scene's whispers, laughter, and dialogue, then give the performance a different voice.
Recast a lesson narration
Give a recorded lesson another voice while keeping the instructor's cadence and emphasis.
Compare voices for a recorded ad
Convert the same spoken take into several voices to compare how each sounds with the recorded performance.
Revoice multilingual recordings
Convert English, Japanese, or French recordings while retaining each recording's language and accent.
More on ElevenLabs Voice Changer Multilingual v2 and Muse Code
Overview
ElevenLabs Voice Changer Multilingual v2 in other agents
Questions about ElevenLabs Voice Changer Multilingual v2 in Muse Code
Can Muse Code use ElevenLabs Voice Changer Multilingual v2?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run ElevenLabs Voice Changer Multilingual v2 like any built-in tool.
How much does ElevenLabs Voice Changer Multilingual v2 cost in Muse Code?
$0.156 per minute. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.
Do I need an ElevenLabs account to use ElevenLabs Voice Changer Multilingual v2 in Muse Code?
No. Spiral runs ElevenLabs Voice Changer Multilingual v2 on its own ElevenLabs account. You sign in to Spiral once and never paste a key.
How long does it take to set up ElevenLabs Voice Changer Multilingual v2 in Muse Code?
About two minutes: install Muse Code, then ask Muse to add the server, then sign in.
Does Muse Code wait while ElevenLabs Voice Changer Multilingual v2 runs?
ElevenLabs Voice Changer Multilingual v2 runs in the background. Muse Code starts the run, checks on it and gives you the audio when it's ready.
What does ElevenLabs Voice Changer preserve?
It changes the voice while retaining the recording's emotion, timing, and delivery. Whispers, laughter, and accent can carry through, so the original performance matters.
Which languages does Multilingual v2 support?
It supports 29 languages, including English, Japanese, Chinese, German, Hindi, and French.
Will choosing a different voice change my accent?
The source recording's accent carries through. Record the accent you want to hear in the finished speech.
How long can a recording be?
Use chunks of five minutes or less. ElevenLabs' voice changer guidance specifies five minutes, although a separate help article lists ten minutes for Multilingual v2.
How should I direct an expressive performance?
Record the delivery you want, including whispers, laughter, and emotional emphasis. Those details give the conversion a performance to preserve.
Start using ElevenLabs Voice Changer Multilingual v2 in Muse Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Muse Code:
set up https://spiral.ai/SKILL.md


