Indie Signals Logo - Early AI & Open Source TrendsIndie Signals

Topic Hub

Best Text-to-Speech Open Source Projects

This hub collects the best open source projects in Text-to-Speech and ranks them by both momentum and authority.

Data window: Last 7 days (with 24h tie-breakers for Trending now)

Last updated: Sep 18, 2026

Projects

61

GitHub stars

8.3K

Hugging Face likes

21.6K

Replicate runs

5.5M

Authority projects

Projects with the strongest long-term signal in Text-to-Speech, ranked by total stars, likes, or runs on their primary platform.

qwen3-tts

Converts text into natural-sounding speech across multiple languages.

Replicate
2.2Mruns

grok-text-to-speech

Convert text to natural-sounding speech with high-fidelity audio output and support for multiple languages.

Replicate
2Mruns

gemini-3.1-flash-tts

Convert text into natural-sounding speech with expressive voices.

Replicate
997.3Kruns

tts-1.5-mini

Fast text-to-speech synthesis with low latency and multilingual support.

Replicate
174Kruns

tts-1.5-max

High-quality text-to-speech synthesis with low latency and emotion control.

Replicate
142.1Kruns

realtime-tts-2

Generate natural, expressive speech from text in real-time.

Replicate
25.9Kruns

hexgrad/Kokoro-82M

Affordable text-to-speech model for various applications.

Hugging Face Model
6.9Klikes

Qwen3-TTS

Generate high-quality speech with expressive and natural voice.

GitHub
5.4Kstars

Qwen/Qwen3-TTS

Generate realistic speech from text with custom voices or voice cloning capabilities.

Hugging Face Space
2.2Klikes

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Generate high-quality speech from text with advanced voice control and emotional expression.

Hugging Face Model
1.4Klikes

openbmb/VoxCPM2

Generate high-quality audio from text in multiple languages with a versatile Text-to-Speech model.

Hugging Face Model
1.3Klikes

k2-fsa/OmniVoice

Generate natural-sounding speech from written text with optional voice cloning.

Hugging Face Space
1.3Klikes

Hidden gems

Smaller projects with unusually strong momentum. We look for lower total metrics plus positive 7-day growth.

personalized-podcast

Turn any content into a personalized AI podcast episode with customizable hosts and discussion.

GitHub
213stars
2137d

Persian-IPA-to-Speech-F5

GitHub

GitHub
195stars
1427d

breeze-tts

GitHub

GitHub
172stars
1137d

tencent/AuK

Hugging Face Model

Hugging Face Model
289likes
1757d

mistralai/Voxtral-Realtime-WebGPU

Generate speech from text in real-time using GPU acceleration.

Hugging Face Space
77likes
367d

OpenMOSS-Team/MOSS-TTS-Nano

Clone a voice and generate speech from text

Hugging Face Space
41likes
217d

d10g/f1commentator

Generate live F1 race commentary with audio and robot gestures.

Hugging Face Space
44likes
327d

BreezeBlue/breeze-tts-2-demo

Hugging Face Space

Hugging Face Space
80likes
347d

qwen3-TTS-studio

Generate high-quality voices and podcasts with ease using this professional-grade interface.

GitHub
172stars
827d

KittenML/KittenTTS-Demo

Generate natural-sounding speech from text instantly with adjustable voice and speed options.

Hugging Face Space
42likes
207d

rednote-hilab/dots.tts

Generate natural speech from written text in real time.

Hugging Face Space
29likes
167d

kitten_tts_rs

Converts text into high-quality speech synthesis with adjustable speed and voice options.

GitHub
221stars
917d