GraphCanon updated 3w · GitHub synced 3w · 37 views this month
Decision brief
Speech-AI-Forge is ideal for developers and teams requiring versatile text-to-speech solutions with extensive customization options through an easy-to-use WebUI or API server interface.
Good fit when
- When you need fine-grained control over TTS styles, including speed, pitch, volume, and voice quality enhancement.
- In situations where support for multiple TTS models such as ChatTTS, CosyVoice, FishSpeech, GPT-SoVITS, or F5-TTS is required.
Avoid when
- If your project does not require support for multiple TTS models; Speech-AI-Forge offers versatile model choices which may complicate setup.
- In cases where only basic ASR functionality is needed, as Speech-AI-Forge's ASR capabilities might be seen as overkill or too complex for simple use-cases.
- Pricing:
- freemium - The core project is free under the AGPL-3.0 license with no direct monetary charge to access functionalities, but advanced features may have associated operational costs depending on usage and scale.
- Requirements:
- Min 4 GB RAM
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (69d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- 91 low (91 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install Speech-AI-ForgeSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Speech-AI-Forge is focused on text-to-speech (TTS) functionality providing an interface through an API server and a Gradio-based WebUI, featuring extensive customization options for voice styles, models support, and ASR capabilities.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Jul 30, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Jul 30, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Jul 30, 2026
- Languages
- python, javascript
Source: github.language+package.json+pyproject.toml · Jul 30, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Installation and Running
首先，确保 相关依赖 已经正确安装，并查看 模型下载 下载所需模型
启动：
python webui.py
WebUI 功能
点我看详细图文介绍
-
TTS (文本转语音): 提供多种强大的 TTS 功能
- 音色切换 (Speaker Switch): 可选择不同音色
- 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 - 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
- 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
- 内置音色: 提供多个内置音色，包括
- 风格控制 (Style): 内置多种风格控制选项，调整语音风格
- 长文本推理 (Long Text): 支持超长文本的推理，自动分割文本
- 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
- Batch Size: 支持设置
- Refiner: 支持
ChatTTS原生文本refiner，支持无限长文本处理 - 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 - 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 - 人声增强 (Voice Enhancer): 使用
Enhancer模型增强 TTS 输出，提高语音质量 - 生成历史 (Generation History): 保存最近三次生成结果，便于对比和选择
- 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
- 音色切换 (Speaker Switch): 可选择不同音色
-
SSML (语音合成标记语言): 提供高级 TTS 合成控制工具
- 分割器 (Splitter): 精细控制长文本的分割结果
- 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 - From Subtitle: 从字幕文件生成 SSML 脚本，方便一键生成语音
- 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
-
音色管理 (Voice Management):
- 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
- 试音功能 (Test Voice): 上传音色文件，进行简单的试音和效果评估
- ChatTTS 调试工具: 专门针对
ChatTTS音色的调试工具- 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
- 音色融合 (Blend): 融合不同种子创建的音色，获得新的语音效果
- 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 获取更多音色资源
-
ASR (自动语音识别):
- ASR: 使用 Whisper/SenseVoice 等模型进行高质量的语音转文本（ASR）
- Force Aligment: 使用 Whisper 模型可以进行【文稿匹配】提高识别准确性
-
工具 (Tools):
- 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
For agents
This page has a .md twin and JSON over the API.