Free
Start creating with essential AI voice tools.
$0/mon
- Basic voice cloning model
- Unlimited Voice Clones
- Unlimited Voice Slots
- 10,000 chars/mo (~12 mins)
- Max 500 chars per request
- Personal use only — not for commercial use
Simple, transparent pricing to empower every creator.
Start creating with essential AI voice tools.
$0/mon
For creators ready to publish with commercial rights and faster output.
$4.9/mon
For high-volume creators who need stronger voice control and higher throughput.
$9.9/mon
Yes. The Free plan includes the Standard V1.5 model, unlimited voice slots, and 10,000 characters per month (about 12 minutes of audio), with up to 500 characters per generation — for personal use only. You stay on the Free plan until you choose to upgrade.
Free includes Standard V1.5 and 10,000 characters/month for personal use. Starter ($4.9/month, or $3.9/month billed annually) adds commercial rights, Voice Design, 150,000 characters/month, up to 2,000 characters per generation, and 2 devices. Creator ($9.9/month, or $7.9/month billed annually) adds the Enhanced V2.0 model, 8-dimension emotion control, 300,000 characters/month, up to 5,000 characters per generation, 5 devices, and 5 concurrent generations.
Commercial use is included from the Starter plan and covers monetized videos, ads, courses, podcasts, audiobooks, and client work. The Free plan is for personal use only. You must also have the rights to any voice sample you upload.
Free: 500 characters per generation and 10,000 per month. Starter: 2,000 per generation and 150,000 per month. Creator: 5,000 per generation and 300,000 per month.
Upload a sample from 5 seconds to 5 minutes (MP3, WAV, M4A, or MP4, up to 30MB). In practice, a clean clip of about 15 seconds with a single speaker and no background music gives the most stable results.
Standard V1.5 is on every plan and prioritizes speed and stability for everyday content. Enhanced V2.0, available on Creator, offers higher fidelity and 8-dimension emotion control — happy, angry, sad, fearful, disgusted, melancholic, surprised, and calm — adjusted independently of the voice's timbre.
The API is in development and coming soon. Today the full workflow — cloning, Voice Design, and generation — runs directly in your browser, with nothing to install.
Uploaded samples are used only to build your voice model and generate your requested audio — they are not used to train the AI. Voice models from free users are deleted within 7 days; subscriber models are saved for later use. Generated audio stays in your history for 7 days for replay and re-download.