indextts

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Audiobook creation app supporting too many TTS models (Qwen3-TTS, OmniVoice, VibeVoice, etc), focused on high-quality output. Plus audio-synced reader web app and standalone server component.

MLX implementation of IndexTTS (v1.5 & v2.0) — high-quality text-to-speech with voice cloning and emotion control, optimized for Apple Silicon

多引擎语音合成平台：VoxCPM2 与 IndexTTS2 引擎，声音克隆、音色设计、LoRA 微调、多角色剧本配音、情感控制，OpenAI 兼容 API，中英日韩界面，一键安装启动 | Multi-engine TTS platform: VoxCPM2 + IndexTTS2, voice cloning, voice design, LoRA fine-tuning, multi-character dubbing, emotion control, OpenAI-compatible API, zh/en/ja/ko UI, one-click install

Windows launcher and unified workbench for IndexTTS 2.5 voice cloning and TTS.

IndexTTS2 精确停顿控制（[pause:N]）ComfyUI 节点包：句中与句号前后停顿精确调整，平均偏差 13ms；支持批量生成、候选试听验收、SRT 字幕与 seed 复现。Precise pause control ([pause:N]) ComfyUI nodes for IndexTTS2 — waveform-domain pause editing in-sentence and around periods, ±13ms, with batch generation, candidate acceptance and SRT subtitles.

T8star-Aix IndexTTS 2.5 Windows Electron desktop integration

IndexTTS 2.5 MLX 8-bit for Apple Silicon with an official /gen_single Gradio-compatible service on port 7862

Precise pause control ([pause:Nms]) for IndexTTS 2.5: whisper dual-anchor localization + energy valley insertion + optional code-level pause detector (LR+LSTM). Minimal 7-line patch for official webui.py. 中英双语。

Bilingual IndexTTS 1.5 API service with local WebUI, voice management, and queued generation / IndexTTS 1.5 双语 API 服务，集成本地 WebUI、音色管理与队列式生成

AI Agent 可复用的本地语音生成技能 —— 通过 gradio_client 调用本机正在运行的 IndexTTS2 WebUI，复用已加载模型生成口播/配音（不重复加载、不占双份显存）。

Open a GitHub issue, get zero-shot voice-cloned speech back as a Release — IndexTTS-2 running on a free Google Colab T4 GPU, orchestrated entirely by GitHub Actions.

One-click IndexTTS deployment for RunPod

Production-derived TTS and HLS generation engine for long-form AI dubbing.

Archived: superseded by ComfyUI-Hydra-InferWorks v1.0.0

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Local multi-voice audiobook pipeline for the Shadow Slave web novel - LLM diarization + IndexTTS2 emotional voice cloning on a single 12 GB GPU

Run high-quality text-to-speech models locally on your CPU with low latency and no GPU requirements.