diodiogod/TTS-Audio-Suite

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual), F5-TTS, Higgs Audio 2, 3, and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

What it solves

TTS Audio Suite is a comprehensive ComfyUI extension that unifies multiple Text-to-Speech (TTS), Voice Conversion (VC), and Automatic Speech Recognition (ASR) engines into a single modular workflow. It solves the fragmentation of audio AI tools by providing a unified interface for high-quality voice synthesis, voice cloning, and subtitle-synchronized audio generation.

How it works

The suite integrates a vast array of AI audio engines (such as F5-TTS, Higgs Audio, MOSS-TTS, and RVC) through a modular architecture. It features a "Main environment" based on Transformers 5 for modern engines and "Isolated runtimes" to maintain compatibility with legacy stacks. The system supports advanced control mechanisms like inline emotion/style tags, character switching, and a specialized SRT processing node that aligns generated audio with subtitle timings using intelligent shifting logic to prevent overlaps.

Who it’s for

It is designed for ComfyUI users, content creators, and animators who need professional-grade voiceovers, precise subtitle synchronization, and the ability to clone voices or train custom RVC models within a visual node-based environment.

Highlights

  • Massive Engine Support: Integrates 19+ engines including F5-TTS, DramaBox, Higgs Audio, and RVC.
  • SRT Integration: Specialized nodes for transcribing to SRT, rebuilding subtitles, and estimating timing from plain text.
  • Advanced Voice Control: Supports inline tags for emotions, laughter, sighs, and prosody, as well as character and language switching.
  • Voice Design & Training: Includes tools for reference-free voice design and integrated RVC model training.
  • Silent Speech Analysis: Uses MediaPipe to detect mouth movements in silent video to create base timing templates for TTS.
  • Audio Tooling: Features built-in vocal/noise removal, wave analyzers, and intelligent text chunking.

Related

  • Project
    wildminder/ComfyUI-VibeVoice

    ComfyUI‑VibeVoice adds Microsoft VibeVoice TTS/ASR nodes to ComfyUI, supporting multi‑speaker, voice‑cloning, quantised models and realtime single‑speaker generation, with automatic model download and VRAM management.

  • Project
    chenpipi0807/ComfyUI-Index-TTS

    A ComfyUI extension that implements IndexTTS for high-quality voice cloning and text-to-speech, featuring multi-lingual support, emotion control, and multi-character novel parsing.

  • Project
    flybirdxx/ComfyUI-Qwen-TTS

    ComfyUI custom nodes for Qwen3-TTS that enable high-quality text-to-speech, zero-shot voice cloning, and natural language-based voice design.

  • Project
    rsxdalv/TTS-WebUI

    A unified web interface and manager for a wide variety of open-source text-to-speech, audio generation, and audio conversion AI models.

  • Project
    Xerophayze/TTS-Story

    TTS‑Story is a web UI for multi‑voice audiobook creation. It lets you tag speakers, design or clone voices (via Google Gemini Cloud or many local models), run a queue of TTS jobs, review audio in‑app, and export MP3/M4B. Supports 20+ engines, GPU/CPU isolation, bulk voice casting, directed‑narration, and optional LLM text‑prep.