Supertone
Supertone is a Voice Intelligence Platform offering AI text-to-speech, real-time voice changers, and voice API for creators and businesses.
Last verified:
What is Supertone?
Supertone is a comprehensive voice intelligence platform that provides AI-powered voice technology solutions for expressive speech synthesis, real-time voice transformation, and audio enhancement. The platform offers multiple products including Play (text-to-speech), Shift (real-time voice changer), Clear (de-noise & de-reverb plugin), and Air (reverb & EQ dialogue match plugin), plus a production-grade API for developers.
Key features include natural and expressive speech synthesis with Sona 2 (the latest TTS model supporting 23 languages), 150+ premium character voices with emotional styles, voice cloning from ~10-second audio samples, real-time voice transformation with low latency, and professional audio plugins for post-production. The API supports 31 languages with character identity preservation, fully adjustable pitch/intonation/speed, and official Python & TypeScript SDKs.
Supertone is designed for content creators (video editors, streamers, V-Tubers), media creators, game developers, VRChat users, post-production engineers, dialogue editors, re-recording mixers, entertainment and AI teams, businesses building voice agents, and developers integrating voice into products. It supports gaming, V-Tubing, virtual worlds, audiobooks, multilingual content localization, AI dubbing, and accessibility features.
Supertone pricing
Pricing model: Free
Free tier: $0/month with ~5 min/month usage, 3,000 credits, full voice access, unlimited voice cloning (script reading required), unlimited downloads, commercial use with 'Supertone' attribution, up to 20 API requests/min. Starter: $2.99/month (or $3.99/month for Shift) with ~30 min/month, 20,000 credits, voice cloning via audio upload, unlimited desktop Supertonic first month only, unlimited commercial use. Creator/Creator Recommended: $14.99/month with ~300 min/month (Supertonic) or ~150 min (Sona), 100,000 credits, AI dubbing, word/line spacing control, up to 30 API requests/min, bulk creation/editing. Pro: $79.99/month with unlimited Supertonic desktop, ~1600 min Supertonic web or ~800 min Sona, 500,000 credits, unlimited desktop forever for Pro, up to 60 API requests/min. Shift Starter: $1.99/month (50% off) for 40 voices. Shift Pro: $14.99/month. Perpetual voice: $149.99/voice lifetime. Enterprise: Custom credits/pricing, flexible API rate limits, dedicated account manager, priority support. Open Beta special: $24 for 3-month unlimited access during beta period.
Supertone pros
- 100+ character voices available free monthly with credits
- Sona 2 delivers human-like performance with deep context understanding
- Voice cloning from just ~10-second audio samples
- 23 languages supported for TTS and voice cloning
- 31 languages available through API with character identity preserved
- Low latency real-time voice transformation close to true real-time
- No GPU required for high-quality voice conversion on any device
- Three simple knobs in Clear plugin for easy de-noise & de-reverb
- Air captures early reflections accurately for natural ADR matching
- Real-time processing capability perfect for streamers
- Minimum artifacts in voice separation neural network
- 150+ premium voices with 50+ emotional styles
- Fully adjustable pitch, intonation, and speed via voice_settings
- Official Python and TypeScript SDKs with async support
- Commercial use included with proper attribution on Free plan
- Works in all DAWs supporting VST3, VST, AU, and AAX formats
- Native Apple Silicon support for m1, m2, m3 maximum performance
- Voice cloning via audio file upload on Starter plan
- AI dubbing feature included on Creator plan
- Unlimited desktop Supertonic generation for Pro subscribers
Supertone cons
- Credits reset monthly and do not roll over to next month
- Free plan limited to ~5 minutes monthly usage
- Voice generation pauses when credits exhausted with no overage charges
- Starter plan desktop Supertonic unlimited only for first month
- Sona 2 consumes 2x credits compared to Supertonic model
- Windows requires 64-bit only (32-bit not supported)
- Free plan requires 'Supertone' attribution for commercial use
- Open Beta purchases not refundable due to change of mind
- MacOS minimum version 10.13-10.14 depending on product
- Premium voices require paid subscription beyond Free tier
Frequently asked questions about Supertone
What happens when my credits are used up?
When your credits are used up, voice generation is temporarily paused. There are no automatic overage charges, and you can resume use once your credits are refilled in the next billing cycle. You can also upgrade your plan to receive additional credits immediately.
Do credits roll over to the next month?
Credits are reset every month and do not roll over to the next month. New credits are issued for your plan at the start of each billing cycle.
What is the difference between Supertonic and Sona models?
Supertonic is Supertone's lightweight, high-efficiency model — with the same credits, it can generate about 2× the audio compared to Sona. Sona delivers the highest-quality expressiveness but consumes 2× the credits of Supertonic. Choose the one that fits your needs.
Can I use Supertonic without consuming credits on Desktop?
When using the Supertonic model in the Desktop app, you can generate audio without consuming credits. This applies to the first month only for Starter and Creator, while Pro subscribers can enjoy it throughout their entire subscription period. Sona 2 still consumes credits in the Desktop app.
How many languages does Supertone support?
Supertone Play's Sona 2 supports 23 languages for both preset voices and cloned voices. The Supertone API supports 31 languages with character identity preserved across each language.
What is voice cloning and how does it work?
Voice cloning trains Supertone Play with your voice effortlessly using just one-time training, registering your voice in the voice library for continuous use. You can train in any language and speak naturally in 23 languages with your cloned voice. For the API, voice cloning works from approximately 10-second audio samples.
What audio plugin formats does Clear support?
Clear is offered in AU, VST3, VST, and AAX audio plug-in formats, and can be used in all DAWs that support third-party plug-ins. It supports industry standard sample rates of 44100Hz, 48000Hz, and 96000Hz.
What plugin formats does Air support?
Air is offered in VST3, AU, and Audiosuite (AAX) plug-in formats, and can be used in all DAWs that support third-party plug-ins. It was built as an Audiosuite plug-in first for instant capture of clips and offline processing within Pro Tools projects.
Can I use Supertone for commercial projects?
Yes, commercial use is available. The Free plan allows commercial use with 'Supertone' attribution. Starter, Creator, and Pro plans include unlimited commercial use without attribution requirements. Enterprise plans offer custom solutions for large-scale businesses.
What is Shift best used for?
Shift is a real-time voice changer designed for gaming (crack jokes in an FPS lobby), V-Tubing, role-playing in VRChat, virtual worlds, and debuting fresh personas on stream. It offers 100+ character voices, customizable parameters like pitch and joy, epic effects, best-in-class low latency, high quality conversion, and works without requiring a GPU.