MOSS-TTS

Apache-2.0 · Commercial use OK

MOSS-TTS is a free, open-source alternative to ElevenLabs. It can be used without subscription fees — and its source code is open for anyone to inspect, modify and self-host.

License
Apache-2.0
Replaces
1 commercial tools
GitHub stars
⭐ 4k
Written in
Python
Forks
366
Last activity
1 months ago
Growth (7 days)
+42 ★
audioaudio-tokenizerllmmultimodaltext-to-speechvoice-cloning
GitHub starsLast commitContributors
View on GitHubProject page ›

About

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, vo Its license (Apache-2.0) is permissive: free to use, modify and redistribute — including inside commercial and proprietary products.

What switching gets you

An open-source alternative to

ElevenLabs

Other alternatives worth a look

Dograh · ⭐ 5.5k · PythonSelf-hosted voice-AI platform, bring your own keys, on-prem friendly.Voicebox · ⭐ 51.8k · TypeScriptLocal-first AI voice studio: clone voices, dictate, create.Voice-Pro · ⭐ 12.7k · PythonVoice suite for podcasters and creators: cloning, dubbing, subtitles.OmniVoice Studio · ⭐ 12k · PythonLocal voice cloning, dubbing, dictation and audiobook creation.VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life CloningCosyVoiceMulti-lingual large voice generation model, providing inference, training and deployment full-stack ability.