#text-to-speech · AI & ML

Text-to-speech

Speech synthesis and voice cloning, from open models to the engines and apps that run them.

This week (Oct 27 – Nov 2), the top-ranked are VoiceStudio (+10,060), IP-Bot (+198) and chanh-dien-online (+155). The 87 ranked repos gained 22,382 stars, 13% fewer than the week before.

Updated Nov 2, 11:35 UTC · ranked every hour from GitHub’s daily star counts

Updated 27 min ago

GitHub topic ↗

Emerging this week

Showing 10 of 11

How Upstar ranks

Listed by acceleration against their usual week; the score is the rankings’ own: stars gained in 7 days ÷ √(stars before, minimum 100).

1
gradium-ai/xn-ptts Phonon TTS inference using xn 47× its usual pace (~2 a week) Rust Rust · 412 total Healthy
Gained in 7 d +94 Score 5.3 Total 412
2
HoppouAI/Breeze-TTS-2.cpp Bilingual English and Mandarin text to speech in C++ and GGUF. Voice design, cloning, direction and experimental voice conversion. Vulkan backend, streaming HTTP and WebSocket server, web UI and a C API. 22× its usual pace (~4 a week) C++ C++ · 142 total Healthy
Gained in 7 d +89 Score 8.9 Total 142
3
Yuuyuko-uu/dsh-tts-bridge DSH 朗读桥：会话里的话自动交给 DeepSeek 网页端朗读，声音从你自己的电脑里出来 85× its usual pace (~1 a week) JavaScript JavaScript · 214 total
Gained in 7 d +85 Score 7.5 Total 214
4
breezeblue-ai/breeze-tts Official PyTorch inference for Breeze TTS 2 8× its usual pace (~48 a week) Python Python · 1.3k total Mixed signals
Gained in 7 d +400 Score 13.2 Total 1.3k
5
beiyege-01/dsh-voice-ai-girlfriend 语音 AI 女友（Voice AI girlfriend for DeepSeek Harness）：Whisper 语音输入 + Qwen3-TTS 声音克隆 + 句子级流式朗读 + 数字人动画窗。插话/排队双模式，说话即打断。 7× its usual pace (~23 a week) TypeScript TypeScript · 882 total Mixed signals
Gained in 7 d +154 Score 5.7 Total 882
6
bayshier/voicestudio-zh VoiceStudio 中文版：开源、完全本地的 ElevenLabs 替代品——语音克隆、语音设计、视频配音、听写、转写与有声书，646 种语言（译自 debpalash/VoiceStudio，AGPL-3.0） 5× its usual pace (~12 a week) Python Python · 195 total
Gained in 7 d +57 Score 4.9 Total 195
7
aashish254/Aniflow 🎬 Autonomous AI Studio for Manhwa & Webtoon Recaps — Vision Pipeline (YOLOv8 + Magi v2), Multi-Voice TTS & Video Synthesis 4× its usual pace (~6 a week) Python Python · 68 total
Gained in 7 d +26 Score 2.6 Total 68
8
Saganaki22/ComfyUI-Breeze-TTS-2 Breeze TTS 2 nodes for ComfyUI: voice clone, voice design, and voice direction with bilingual (EN/ZH) speech, inline vocal events, INT8 ConvRot quantized builds, and full ComfyUI / AIMDO dynamic-VRAM integration. 3× its usual pace (~9 a week) Python Python · 141 total Mixed signals
Gained in 7 d +24 Score 2.2 Total 141
9
sahilmahendrakar/paradee An 8M-parameter English text-to-speech model distilled from Kokoro-82M. 9 MB, runs 18x real time on one CPU thread. 2× its usual pace (~29 a week) Python Python · 186 total
Gained in 7 d +68 Score 6.3 Total 186
10
Hiruynk/AnifLive-TTS A low-latency, high-quality multilingual voice-cloning TTS runtime After quiet weeks Python Python · 36 total Mixed signals
Gained in 7 d +23 Score 2.3 Total 36

Back to the ranking Past weeks: Oct 26 Oct 19