Topic Hub

Best Speech Synthesis Open Source Projects

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

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

Last updated: Sep 10, 2026

Projects

15

GitHub stars

1.8K

Hugging Face likes

4.5K

Replicate runs

3.2M

Authority projects

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

speech-2.8-turbo

Convert text into natural speech with voice cloning and emotion control.

Replicate
1.5Mruns

speech-2.6-turbo

Generate realistic speech from text with emotional tone and multilingual support.

Replicate
1.2Mruns

speech-2.8-hd

Generate high-fidelity audio with flexible emotion control and voice cloning capabilities.

Replicate
232.1Kruns

speech-2.6-hd

Generate studio-quality audio from text with nuanced prosody and premium voices.

Replicate
179.8Kruns

nvidia/personaplex-7b-v1

Real-time speech-to-speech conversational model for natural interactions

Hugging Face Model
2.5Klikes

tada

Generate natural-sounding speech from text with variable duration and prosody.

GitHub
840stars

mistralai/Voxtral-Mini-4B-Realtime-2602

Real-time speech transcription model for multiple languages.

Hugging Face Model
725likes

ComfyUI-Qwen-TTS

Generate high-quality speech from text with custom voice characteristics.

GitHub
696stars

openbmb/VoxCPM-Demo

Generate custom speech with voice design or cloning capabilities.

Hugging Face Space
629likes

FlashLabs/Chroma-4B

Advanced multimodal model for real-time voice conversations and voice cloning.

Hugging Face Model
348likes

Supertone/supertonic-3

Generate speech from text in multiple languages quickly and privately.

Hugging Face Space
209likes

voicebox

Synthesize natural sounding voices and generate speech locally on your machine.

GitHub
151stars

Hidden gems

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

multimodalart/scenema-audio

Generate custom voices with effects and emotions using AI.

Hugging Face Space
31likes
317d

multimodalart/kugelaudio

Generate realistic speech voices in multiple languages from text input.

Hugging Face Space
72likes
377d

Supertone/supertonic-3

Generate speech from text in multiple languages quickly and privately.

Hugging Face Space
209likes
347d

FlashLabs/Chroma-4B

Advanced multimodal model for real-time voice conversations and voice cloning.

Hugging Face Model
348likes
237d

voicebox

Synthesize natural sounding voices and generate speech locally on your machine.

GitHub
151stars
107d