sdsds222/Unitale
一个基于Indextts和Qwen3TTS的 AI 有声书制作工具。利用 LLM 自动拆解剧本与识别情绪，集成多角色 TTS 语音合成（可智能分析音色并使用Qwen3TTS语音设计模型从音色描述文本生成音色），支持音效(SFX)、背景音乐(BGM)混音及实时台词音频滤波器的自动插入和匹配，可直接在浏览器导出 wav 成品，本工具本体无需配置环境即可跨平台在浏览器使用。
This tool helps creators turn written scripts into professional-sounding audiobooks and audio dramas. You provide a script, and the system intelligently analyzes it to generate spoken dialogue for multiple characters, adds appropriate sound effects and background music, and even applies audio filters for different scenes. It's designed for writers, podcasters, or content creators who want to produce high-quality audio content without needing extensive audio production skills.
Use this if you want to automatically create engaging audiobooks or audio dramas from your scripts, complete with multi-character narration, sound effects, and background music, all within your web browser.
Not ideal if you require extremely fine-grained, manual control over every audio parameter or if your project demands custom voice actors rather than AI-generated voices.
Stars
89
Forks
24
Language
HTML
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sdsds222/Unitale"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ShaerWare/AI_Secretary_System
📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2,...
EmZod/Speak-Turbo
Ultra-fast local TTS for AI agents. ~90ms to first sound.
HCID274/JianYan
基于 SenseVoice 的 Windows 本地语音转文字工具，支持 OpenAI 格式 API 润色，低延迟，高精度。
jitendrakw09/Voice-Sangam
Voice Sangam is a modern text-to-speech platform built with Next.js 16, delivering fast,...
tellang/sonote
AI 에이전트를 위한 소리 노트 — 실시간 한국어 음성 전사 CLI