Basic: your device's built-in voice
The Basic tier uses your device's built-in text-to-speech engine. This is the voice that comes with your phone or tablet.
- Cost: Free, always available
- Quality: Varies by device. Newer phones tend to have better built-in voices
- How it works: The speech is generated entirely on your device with no download needed
Basic is the fallback voice. If Standard voices have not finished downloading, Epivo uses Basic automatically.
Standard: enhanced AI voices from Piper
Standard voices are powered by Piper, an open-source neural text-to-speech engine. These voices sound noticeably more natural and clear than Basic.
- Cost: Free
- Quality: Natural-sounding with good pronunciation and pacing
- How it works: Voice models are downloaded to your device (a small one-time download per voice). Speech is then generated locally on your device
Standard voices are the default for most learners. They offer a significant quality upgrade over Basic at no cost. Note that while the voice itself runs on-device, an internet connection is still required for speech recognition and AI processing.
Premium: studio-quality voices from ElevenLabs
Premium voices use ElevenLabs, a leading voice synthesis service. These are the most lifelike voices available in Epivo.
- Cost: Part of the Mini or Max subscription
- Quality: Studio-quality, highly expressive, and the closest to a real human voice
- How it works: Speech is generated in the cloud and streamed to your device
Premium voices make the tutoring experience feel remarkably human. If voice quality matters to you, this is the tier to choose.
Which tier should I use?
For most learners, Standard voices provide an excellent experience at no cost. They are clear, natural, and run efficiently on your device.
If you want the most immersive, lifelike experience, Premium voices on the Mini or Max plan are worth trying. The difference is especially noticeable during longer sessions.
Basic is there as a reliable fallback. You do not need to select it manually — Epivo uses it automatically when other tiers are not available.
Frequently asked questions
- Can I switch between voice tiers?
- Premium voices are tied to teacher personas in the Teachers menu (visible on Mini and Max plans). Standard is the default for all users. Basic is used automatically as a fallback.
- Do Standard voices use mobile data?
- The initial voice model download uses data. After that, the voice itself runs on your device. However, sessions always require an internet connection for speech recognition and AI responses.