Step 1
Enter Your Text
Paste up to 4000 characters of text — any language, any topic. VoxCPM2 handles punctuation, abbreviations, and numerals automatically.
VoxCPM2 · Zero-Shot cloning
VoxCPM2 Voice Cloning:
Zero-Shot Cloning with Style Control
Upload a short permitted audio sample and VoxCPM2 uses it as a reference for voice cloning — no separate training job or fine-tuning queue. You can then test multilingual speech with a consistent speaker identity, and if you're just getting started, explore VoxCPM2.
Loading generator...
Hear Voice Cloning in Action
Compare reference clips with cloned output — without leaving this page.
Reference
Video & podcasts · Original voice
Cloned voice
“Keep the host’s voice for intros, ads, and pickups — now generated, not re-recorded.”
Channel host voice · English → cloned English
Reference
Product & app localization · Original voice
Cloned voice (localized)
“Same brand voice, localized script — no new recording session.”
Marketing voice · English → localized output
Reference
Audiobooks & narration · Original voice
Cloned narrator
“Match a narrator’s timbre for sequels and translated editions.”
Narrator voice · Original → cloned
How VoxCPM2 AI Voice Cloning Works
Step 2
Choose Your Voice
Choose a built-in reference or upload a short permitted audio file to create a cloned speaker profile. VoxCPM2 supports zero-shot Voice Cloning without a separate training step.
Step 3
Generate, Play, and Download
Click Generate Speech, review the output, then download it as .wav or copy a share link for your project team.
Why VoxCPM2 Has Powerful AI Voice Cloning
A practical voice cloning workflow for teams that need permission-aware references, multilingual tests, and commercial-use clarity.
Closer to the real speaker
VoxCPM2 is designed for natural zero-shot cloning, with the goal of preserving speaker identity while producing expressive multilingual speech.
Speaker match depends on reference quality, language, text, and generation settings.
30 languages, one profile
Clone once from English (or any language) and generate Mandarin, Arabic, Spanish, and more — same voice, no per-language re-recording.
Useful for localization tests when you need a consistent speaker identity across markets.
Zero-Shot, zero waiting
No fine-tuning queue, no GPU hours, no dataset labeling. The same base model handles TTS, cloning, and Voice Design.
Zero-shot workflow: use reference audio directly instead of training a custom model first.
Free testing · paid commercial use
Test VoxCPM2 online with starter credits, then use a paid plan when you need hosted commercial-use rights.
Self-hosting is governed by the underlying model license and your own deployment terms.
VoxCPM2 vs. ElevenLabs — Voice Cloning Compared
A high-level snapshot for builders comparing hosted access, language coverage, self-hosting, and voice design. Product details can change, so treat this as planning guidance.
| Feature | VoxCPM2 | ElevenLabs |
|---|---|---|
| Languages supported | 30 | 32 |
| Online access | Free starter tier | Paid plans |
| Open source & self-host | Apache 2.0 | Proprietary |
| Zero-Shot cloning | Yes (short ref) | Yes (paid tiers) |
| Voice design from text | Yes | No |
Product features and pricing may change. Review the current plan details before relying on a tool for production work.
Who Uses VoxCPM2 AI Voice Cloning
Use cases where a permitted reference voice helps teams test or produce multilingual audio more consistently.
Video & Podcasts
Create intros, pickups, and draft narration in a voice you have rights to use, without booking a new recording session for every small change.
Product & App Localization
Test localized scripts with a consistent brand voice across markets, then review pronunciation and tone before publishing.
Audiobooks & Narration
Produce approved pick-ups, revisions, or translated drafts while keeping narrator identity consistent across related material.
Accessibility & Assistive
Prototype assistive audio and interface speech in a familiar permitted voice, including cross-lingual tests from one reference sample.
VoxCPM2 Pricing Plans for
TTS, Voice Cloning, and Voice Design
Start with transparent credit-based pricing for Text to Speech, Voice Cloning, and Voice Design, then choose the plan that fits your usage.
One-time Credits
Free
$0/one-time
2 credits (≈ 200 characters / 16 seconds)
Included in plan
- 30-Language Multilingual
- Voice Design
- Controllable Cloning + Ultimate Cloning
- 48kHz Studio-Quality Output
- MP3 / WAV export
- ✗Commercial-use rights
- ✗Priority queue
Basic
$9.9/one-time
(one-time)
800 credits (≈ 80,000 characters / 1.8 hours)
$0.012 per credit
Included in plan
- Everything in Free
- Commercial-use rights
- Email support
- Credits never expire
Pro
✨ Most Popular
$29.9/one-time
(one-time · most popular)
3,000 credits (≈ 300,000 characters / 4.5 hours)
$0.009 per credit — save 20% vs Basic
Included in plan
- Everything in Basic
- Early access to new voice models
- Credits never expire
Business
✨ Best Value
$49.9/one-time
(one-time · best value)
6,000 credits (≈ 600,000 characters / 12 hours)
$0.008 per credit — save 50% vs Basic
Included in plan
- Everything in Pro
- Priority generation queue
- Early access to new voice models
- Credits never expire
Credits never expire on any paid plan. Outputs from Basic, Pro, and Business are licensed for commercial use under our Terms.
Choose one-time credits • No subscription or auto-renewal
✓ One-time credit packs✓ Credits never expire✓ Secure payments✓ Email support
Frequently Asked Questions About AI Voice Cloning
Everything about zero-shot Voice Cloning with VoxCPM2.
VoxCPM2 AI Voice Cloning is a zero-shot Voice Cloning feature that uses a short permitted audio sample as a voice reference. Upload a clean clip you have rights to use, and VoxCPM2 can generate new speech in that speaker style across 30 supported languages.
Clone Permitted Voices. Speak in 30 Languages.
Jump to the generator to test short voice cloning and multilingual speech with free starter credits.