Topic Hub

Best Text-to-Audio Open Source Projects

This hub collects the best open source projects in Text-to-Audio 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

8

GitHub stars

192

Hugging Face likes

1.7K

Replicate runs

15.9M

Authority projects

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

speech-02-turbo

Generate natural-sounding voices with emotional expression and multilingual capabilities in real-time.

Replicate
13Mruns

speech-02-hd

Generate high-quality audio from text with advanced voice synthesis and emotional expression.

Replicate
3Mruns

m-a-p/YuE2-3B

Hugging Face Model

Hugging Face Model
748likes

ACE-Step/Ace-Step1.5

Generate commercial-grade music from text prompts with this open-source model.

Hugging Face Model
649likes

stable-audio-open

Replicate

Replicate
255runs

HeartMuLa/HeartMuLa-oss-3B

Generate music and audio from text inputs using AI.

Hugging Face Model
214likes

bghira-bark

GitHub

GitHub
192stars

ScenemaAI/scenema-audio

Generate expressive speech with emotional arcs and scene awareness from text prompts.

Hugging Face Model
131likes

Hidden gems

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

ScenemaAI/scenema-audio

Generate expressive speech with emotional arcs and scene awareness from text prompts.

Hugging Face Model
131likes
187d

stable-audio-open

Replicate

Replicate
255runs
197d

HeartMuLa/HeartMuLa-oss-3B

Generate music and audio from text inputs using AI.

Hugging Face Model
214likes
07d