{"data":{"slug":"lenml-speech-ai-forge","name":"Speech-AI-Forge","tagline":"🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.","github_url":"https://github.com/lenML/Speech-AI-Forge","owner":"lenML","repo":"Speech-AI-Forge","owner_avatar_url":"https://avatars.githubusercontent.com/u/154655365?v=4","primary_language":"Python","stars":1411,"forks":186,"topics":["agent","asr","chattts","chattts-forge","chinese","colab","cosy-voice","cosyvoice","english","firered","fireredtts","fish-speech","gpt","llama","llm","ssml","stt","text-to-speech","tts","whisper"],"archived":false,"github_pushed_at":"2026-05-21T12:49:07+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/lenml-speech-ai-forge","markdown_url":"https://www.graphcanon.com/tools/lenml-speech-ai-forge.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lenml-speech-ai-forge","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lenml-speech-ai-forge","description":"🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.","homepage_url":null,"license":"AGPL-3.0","open_issues":77,"watchers":21,"ai_summary":null,"readme_excerpt":"## Installation and Running\n\n首先，确保 [相关依赖](./docs/dependencies.md) 已经正确安装，并查看 [模型下载](#模型下载) 下载所需模型\n\n启动：\n\n```\npython webui.py\n```\n<details>\n<summary>WebUI 功能</summary>\n\n[点我看详细图文介绍](./docs/webui_features.md)\n\n- **TTS (文本转语音)**: 提供多种强大的 TTS 功能\n\n  - **音色切换 (Speaker Switch)**: 可选择不同音色\n    - **内置音色**: 提供多个内置音色，包括 `27 ChatTTS` / `7 CosyVoice` 音色 + `1 参考音色`\n    - **自定义音色上传**: 支持上传自定义音色文件并进行实时推理\n    - **参考音色**: 支持上传参考音频/文本，直接基于参考音频进行 TTS 推理\n  - **风格控制 (Style)**: 内置多种风格控制选项，调整语音风格\n  - **长文本推理 (Long Text)**: 支持超长文本的推理，自动分割文本\n    - **Batch Size**: 支持设置 `Batch size`，提升支持批量推理模型的长文本推理速度\n  - **Refiner**: 支持 `ChatTTS` 原生文本 `refiner`，支持无限长文本处理\n  - **分割器设置 (Splitter)**: 调整分割器配置，控制分割结束符（`eos`）和分割阈值\n  - **调节器 (Adjuster)**: 支持调整 `速度/音调/音量`，并增加 `响度均衡` 功能，优化音频输出\n  - **人声增强 (Voice Enhancer)**: 使用 `Enhancer` 模型增强 TTS 输出，提高语音质量\n  - **生成历史 (Generation History)**: 保存最近三次生成结果，便于对比和选择\n  - **多模型支持 (Multi-model Support)**: 支持多种 TTS 模型推理，包括 `ChatTTS` / `CosyVoice` / `FishSpeech` / `GPT-SoVITS` / `F5-TTS` 等\n\n- **SSML (语音合成标记语言)**: 提供高级 TTS 合成控制工具\n\n  - **分割器 (Splitter)**: 精细控制长文本的分割结果\n  - **Podcast**: 帮助创建 `长文本`、`多角色` 的音频，适合博客或剧本式的语音合成\n  - **From Subtitle**: 从字幕文件生成 SSML 脚本，方便一键生成语音\n  - **脚本编辑器 (Script Editor)**: 新增 SSML 脚本编辑器，支持从分割器（Podcast、来自字幕）导出并编辑 SSML 脚本，进一步优化语音生成效果\n\n- **音色管理 (Voice Management)**:\n\n  - **音色构建器 (Builder)**: 创建自定义音色，可从 ChatTTS seed 创建音色，或使用参考音频生成音色\n  - **试音功能 (Test Voice)**: 上传音色文件，进行简单的试音和效果评估\n  - **ChatTTS 调试工具**: 专门针对 `ChatTTS` 音色的调试工具\n    - **音色抽卡 (Random Seed)**: 使用随机种子抽取不同的音色，生成独特的语音效果\n    - **音色融合 (Blend)**: 融合不同种子创建的音色，获得新的语音效果\n  - **音色 Hub**: 从音色库中选择并下载音色到本地，访问音色仓库 [Speech-AI-Forge-spks](https://github.com/lenML/Speech-AI-Forge-spks) 获取更多音色资源\n\n- **ASR (自动语音识别)**:\n\n  - **ASR**: 使用 Whisper/SenseVoice 等模型进行高质量的语音转文本（ASR）\n  - **Force Aligment**: 使用 Whisper 模型可以进行【文稿匹配】提高识别准确性\n\n- **工具 (Tools)**:\n  - **后处理工具 (Post Process)**: 提供音频剪辑、调整和增强等功能，优化生成的语音质量\n\n</details>","github_created_at":"2024-06-01T13:24:45+00:00","created_at":"2026-07-11T12:11:18.15889+00:00","updated_at":"2026-07-11T12:11:29.901398+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"colab","name":"colab"},{"slug":"asr","name":"asr"},{"slug":"chinese","name":"chinese"},{"slug":"cosyvoice","name":"cosyvoice"},{"slug":"chattts","name":"chattts"},{"slug":"chattts-forge","name":"chattts-forge"},{"slug":"cosy-voice","name":"cosy-voice"},{"slug":"agent","name":"agent"}],"trust":{"provenance":{"is_fork":false,"github_id":809025386,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:11:18.873Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":50,"last_release_at":"2026-02-02T04:58:15Z"},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":91,"high_count":0,"last_scan_at":"2026-07-11T12:11:24.538Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-07-11T12:11:24.050Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:11:24.050Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-11T12:11:24.050Z","managed_saas":false},"languages":{"value":["python","javascript"],"source":"github.language+package.json+pyproject.toml","observed_at":"2026-07-11T12:11:24.050Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-11T12:11:24.050Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-07-11T12:11:24.050Z"}}}}