Self-host Breeze TTS 2
Real-time TTS with voice cloning and voice design
- Stars
- 1 090
- Port
- 7860 (Streaming and batch TTS API server)
What is Breeze TTS 2?
An open-weight text-to-speech system for real-time interaction that leads the Artificial Analysis leaderboard among open models. Self-host via Docker, pip, or Python. Three synthesis modes: clone a speaker from reference audio, design a voice from a text description, or direct a cloned voice with instructions. Inline vocal events add laughter, sighs, and more. A streaming HTTP API delivers 24 kHz PCM on port 7860; a batch endpoint processes up to 128 texts. Requires an NVIDIA GPU with 12 GB VRAM (eager) or 24 GB (fast path). Weights on Hugging Face under a non-commercial license; code is Apache-2.0. Commercial use needs a paid BreezeBlue subscription.
Should you self-host Breeze TTS 2?
Breeze TTS 2 scores 54/100 on selfhost.directory (how scoring works) and ranks #35 of 125 in AI. It has 1 090 GitHub stars.
There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.
Setup is advanced: plan for several services and some ongoing maintenance. It is Apache-2.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is ComfyUI (93/100, 143 752 stars). It scores higher overall, so compare the two before you pick. See Breeze TTS 2 vs ComfyUI side by side.
Features
- Batch API
- Bilingual support
- Fast Inference Modes
- GPU-Efficient
- Hugging Face Hub Integration
- Model Digest Verification
- Real-time Streaming
- Single-Concurrency API
- Streaming REST API
- Ultra-Low Latency
- Vocal Events
- Voice Clone
- Voice Design
- Voice Direction
Breeze TTS 2 README
More in Text to Speech
chatterbox-tts-apiChatterbox TTS API is a self-hosted, OpenAI-compatible TTS server with voice cloning and 22-language support. Runs via Docker or Python, integrates with Open WebUI.
ebook2audiobook---LegacySelf-hosted, open-source converter that turns ebooks and PDFs into audiobooks using multiple TTS engines, voice cloning, OCR and 1158 languages.
Fish SpeechSelf-hosted text-to-speech toolkit with voice cloning, multi-speaker scripts and inline emotion tags, plus a TTS API server and WebUI in CUDA or CPU Docker images.
Kokoro FastAPIA self-hosted, open-source FastAPI wrapper for the Kokoro-82M speech model with an OpenAI-compatible endpoint, multi-speaker mixing, SSML, timestamps and a web player.
kokoro-webKokoro Web is a self-hosted, open-source AI voice generator with OpenAI-compatible API and browser UI for natural speech in multiple languages.
OmniVoice-StudioThis self-hosted, open-source ElevenLabs alternative clones and designs voices, dubs video and builds audiobooks in 646 languages, fully local on desktop or Docker.
openai-edge-ttsA self-hosted, open-source text-to-speech API server that mimics OpenAI's /v1/audio/speech endpoint and synthesizes audio for free via Microsoft Edge's TTS voices.
OpenReaderA self-hosted open-source document reader that speaks EPUB, PDF, DOCX, text, and Markdown files aloud with word-level highlighting and audiobook export.
unspeechunSpeech is a self-hosted, open-source TTS proxy with an OpenAI-compatible API for multiple cloud providers like ElevenLabs, Azure, and Deepgram.
wyoming-piperSelf-hosted Wyoming protocol server for Piper TTS, providing neural text-to-speech for Home Assistant and Wyoming clients. Open-source, runs locally via Docker or Python.
airunnerSelf-hosted, open-source desktop AI engine: local LLM chat companions, Stable Diffusion art generation, TTS/STT voice, and a headless Ollama/OpenAI-compatible API.
audiobook-studioSelf-hosted open-source app for producing audiobooks locally using XTTS voice cloning, with optional Voxtral cloud voices. Multi-voice, segment repair, chapter assembly
0 comments