VoiceNPC: AI Voice Clone & TTS

Pick one of 300+ ready-made voices in the Voice Library, or record 5 seconds and clone your own. Type anything and hear it spoken back in 10+ languages, with translation built in. Cloning, speech and translation all run on your device, so your recordings, your text and the audio you make never leave it.

VoiceNPC runs the Qwen3-TTS model locally through Apple's MLX framework. From a short recording it builds a voice fingerprint, then speaks whatever you type in that voice.

Works on iPhone, iPad, and Mac with Apple Silicon.

What you can do:
- Browse the Voice Library: 300+ ready-made voices. Filter by gender, age and pitch, play a demo of any voice, nothing to record or download
- Pro: pick any voice in the Voice Library and generate in all 10 languages
- Clone any voice from a 5–15 second recording, or import one from a video
- Generate speech in English, Chinese, Japanese, Korean, French, German, Spanish, Russian, Italian, Portuguese, and more
- Skip the typing: scan a printed page or pick a photo, and its text appears in the box, read on your device
- Pro: scan several pages at once and get one project section per page
- Translate your text on-device and have your cloned voice read it out in another language
- Pro: pick multiple target languages and generate them all in a single pass
- Preview and edit a translation before you generate the audio
- Pro: create multi-voice projects and give each section its own voice and language, for dialogue, audiobooks, and podcasts
- Choose a style preset (Stable, Natural, Expressive), or adjust the settings yourself
- Export as WAV, or share a voice fingerprint (a .voicenpc file) over AirDrop, Messages, or any app, so others can generate speech in your voice
- Clone as many voices as you like, on the free plan too

Built for creators:
- YouTubers: dub your videos in several languages in your own voice, with no separate translation step
- Podcasters: produce multi-speaker episodes without extra recording sessions
- Audiobook narrators: give every character its own voice
- Voiceover artists: share your voice fingerprint with clients so they can generate lines on demand
- Game developers: generate NPC dialogue in every language you ship

Why it's different:
- Cloning, speech and translation run on-device, and keep working offline after install
- Your recordings and the text you type stay in the app's sandbox, never uploaded
- No cloud processing: your voice never touches a server
- Apple Silicon does the work: the model runs on the chip in your iPhone, iPad, or Mac

How energy works:
- 1 energy ≈ 100 characters of text, about 1–2 sentences
- 25 energy every day, enough for about 5 full generations
- Watch a short video for 25 bonus energy (up to 5 videos a day)
- Earn extra energy by sharing the app daily or inviting friends with your code
- Pro subscribers get unlimited generations with no ads

Go Pro:
- Unlimited generations and no ads, plus multi-language runs, multi-voice projects and generating with any voice in the Voice Library
- Choose a monthly, annual, or one-time lifetime plan

Requires iPhone 13 or later, iPad mini (6th gen) or later, iPad Air (5th gen) or later, iPad (11th gen) or later, or any Apple Silicon Mac.

Terms of Use: Standard Apple Terms of Use (EULA) [https://www.apple.com/legal/internet-services/itunes/dev/stdeula/]