YiziVoice
Voice Cloning · Text to Speech
A one-stop AI voice toolkit for content creators: clone a custom voice from a 20-second sample, generate text-to-speech in 12 emotions, and turn recordings into text with a single click — everything you need for voiceover work.
- tags
- AI 语音音色克隆TTS
About
YiziVoice is an all-in-one AI voice studio for creators: clone your voice, generate voiceovers, and turn recordings into text — all in one workspace.
Core Features
- Voice cloning: record or drop in a 20-second sample to create your own voice persona, with categorized management and reuse
- Text to speech (TTS): type your script, pick a preset or cloned voice, and generate natural speech in one click
- Three control modes: audio tags, free description, or director mode (role / scene / direction) — with one-click AI expansion and built-in examples
- Speech to text (ASR): transcribe recordings automatically with Chinese, English and auto language detection; recordings are saved for replay
- Audio tag system: opening and inline tags covering common voiceover scenarios, customizable and reusable
- History: every generation is saved automatically — jump back to the exact state and keep iterating
Use Cases
Short-video voiceovers, audiobooks, podcasts, course narration, character voice material — anything that needs to speak out loud can be handled by YiziVoice.
Highlights
- ▸Voice cloning: a 20s sample recreates your exclusive voice, categorized and reusable
- ▸Text to speech: 12 emotion styles, natural voiceover in one click
- ▸Three control modes: tags / free description / director mode with AI expansion
- ▸Speech to text: Chinese, English and auto detection, with replay and download
- ▸Audio tag system: opening and inline tags for common voiceover scenarios
- ▸History: generations saved with full state, ready to iterate
- ▸Free to use, right in your browser