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。现已支持背景图片提示词生成功能，可一键导出带情节背景图片和故事音频的mp4视频。
☆237Jul 5, 2026Updated 3 months ago
Alternatives and similar repositories for Unitale
Users that are interested in Unitale are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 一个开源的多角色、多情绪 AI 配音生成平台，支持小说、剧本、视频等内容的自动配音与导出。☆639Aug 16, 2026Updated 2 months ago
- Expand ideas into detailed image prompts with a Chinese SKILL and ComfyUI templates.☆71Oct 22, 2026Updated last week
- 多小说管理与有声生成工具(Multi-Novel Management & Audiobook Generation Tool)☆26Sep 10, 2026Updated last month
- Antigravity API Skill for Antigravity Agent☆45Feb 28, 2026Updated 8 months ago
- NovelFlow 是一个将小说自动转换为视频的 AI 平台。文生图、图生图、图生视频都是基于开源模型及B站大佬分享的工作流。（NovelFlow is an AI platform that automatically converts novels into video…☆116Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 对口型数字人系统 vue+java ,分身系统形象声音克隆对口型文案生成 分站功能 数字人源码 saas系统☆15Oct 27, 2025Updated last year
- Book-to-Audio Studio — 通用多角色有声书制作工具。上传长篇小说 TXT，自动拆解剧本与演员表，试镜绑定音色，批量合成章节 MP3，并支持内嵌同步歌词 / 导出 LRC。☆31Jun 20, 2026Updated 4 months ago
- Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop ker…☆34Aug 29, 2026Updated 2 months ago
- 专为 ComfyUI 打造的开源无限画布 AI 创作工作台：纯前端直连自建与云端算力（首选推荐 LightCC 镜像开箱即用），工作流槽位驱动 UI，涵盖生图/全能参考视频/首尾帧，集成 Canvas Agent 与插件生态。Pure frontend infinite c…☆30Updated this week
- ☆23Dec 24, 2025Updated 10 months ago
- 基于 Qwen3 TTS 的 WebUI☆373Oct 17, 2026Updated last week
- Enables the ComfyUI MiniMax H3 reference-to-video workflow to use a stronger FL2VA model and validated Ref2VA tensor-overlay modes to unl…☆31Sep 25, 2026Updated last month
- AI visual workspace for multi-provider model configuration, image generation, prompts, canvas and local assets☆90Sep 10, 2026Updated last month
- 生成专业视频分镜脚本的 Claude Skill，支持多镜头序列设计和多格式导出☆73Mar 17, 2026Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆21Oct 19, 2025Updated last year
- ☆12Dec 24, 2025Updated 10 months ago
- 推文工具，b站UP主（烂桃侠）地址：https://space.bilibili.com/445842828☆17Apr 12, 2024Updated 2 years ago
- Local-first Windows client for GPT Image generation, multi-reference editing and async task workflows☆15Sep 4, 2026Updated last month
- 为 DeepSeek Harness 打造：选中 AI 回答或思考内容，随时追问、学习、检查与纠偏。☆39Updated this week
- NextJS现代化全栈项目脚手架，前后端一体化设计，帮助开发者(AI)快速产出高质量、可控的代码。☆19Apr 7, 2026Updated 6 months ago
- 基于claude sdk的自动化小说撰写Agent，支持对话，高质量的小说写作与发表☆29Mar 1, 2026Updated 7 months ago
- Ming-omni-tts: Simple and Efficient Unified Generation of Speech, Music, and Sound with Precise Control☆277Feb 26, 2026Updated 8 months ago
- 从参考素材提取项目级视觉系统、视觉圣经与提示词的 Codex Skill☆158Aug 23, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆21Aug 7, 2026Updated 2 months ago
- A reusable agent skill for discovering and validating website internal APIs through instrumented browser traffic and direct HTTP replay.☆13Jul 13, 2026Updated 3 months ago
- 快捷的提示词管理☆32Mar 18, 2026Updated 7 months ago
- 一个为 stable-diffusion-webui 添加 TCD 采样算法的扩展☆12Apr 29, 2024Updated 2 years ago
- 巨物场景生成 SKILL V2.0 — 巨物场景自动导演系统（Giant Scale Scene Director System）☆38Aug 19, 2026Updated 2 months ago
- Obtain scenes from videos using natural language based on the CLIP model☆22Aug 3, 2026Updated 2 months ago
- 赛博竹知了☆16Sep 4, 2026Updated last month
- AI video director skill for Claude Code — From creative ideas to professional storyboards and Seedance 2.0 prompts☆18Apr 8, 2026Updated 6 months ago
- 🔥 ComfyUI-OneAPI: Transform Complex Multi-Step Workflow API Calls → Just One API | 工作流极简化API调用☆13Aug 5, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- VidGlyph · 字映 - 专业视频硬字幕光学解析与精编工坊。基于 Tauri 2 + Rust + Vue 3 + TypeScript 构建。☆23Oct 21, 2026Updated last week
- A web video editor utilizing Vue.js and WebGL/OpenGL, delivering ultimate high performance.Aoles GL 是一个专业级 Web 视频编辑器组件库。☆12Aug 10, 2026Updated 2 months ago
- Web & Comfy☆43Updated this week
- 一个高度可定制化的 AI 角色扮演与互动叙事平台。☆32Updated this week
- Mixed-precision acceleration patch for MiniMax H3 inference on NVIDIA V100☆40Sep 6, 2026Updated last month
- 该项目是一个面向设计师和内容创作者的AIGC工具平台。它通过封装强大的ComfyUI后端，将复杂的节点式AI作图流程，抽象为用户友好的参数化配置界面。用户无需理解底层节点逻辑，只需通过简单的表单选项（如选择模型、输入提示词、调整风格），即可一键生成AI图片☆15Aug 6, 2025Updated last year
- marlin_v100 是一个从 vLLM 主树中提取出来的最小 Marlin 独立开发工作区，聚焦于 Marlin dense 与 Marlin MoE 的源码开发、最小构建和轻量验证。它保留了核心 CUDA/C++ 实现、最小 Python 薄封装、生成器测试与主树回写…☆26Jul 2, 2026Updated 3 months ago