k2-fsa/OmniVoice Alternatives

Use for MIT-licensed few-shot voice cloning with very small datasets and active community.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Use for tokenizer-free multilingual TTS and creative voice design under Apache-2.0.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Use for an open-weight TTS with strong expressiveness and Apache-2.0, though updates are slow.

Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

Use for full-stack training/inference/deployment of multilingual TTS.

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Use for extremely fast real-time voice-cloning TTS (150x realtime).

A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.

Use for an actively developed multilingual TTS family with high-fidelity complex outputs.

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

Use for industrial controllable zero-shot TTS with frequent releases.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Use for stable, expressive streaming TTS and voice cloning from Qwen.

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Use for a lightweight Apache-2.0 inference-only TTS, but less training support.

Spark-TTS Inference Code

Use for multilingual and cross-lingual zero-shot TTS with active maintenance.

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Use for LLM-empowered zero-shot TTS under MPL-2.0 with strong expressiveness.

An Open-Sourced LLM-empowered Foundation TTS System

Use for a TTS built by inverting Whisper, good for research or MIT-licensed experimentation.

An Open Source text-to-speech system built by inverting Whisper.

Use for instant tone-color cloning that pairs with another TTS, not a full TTS engine.

Instant voice cloning by MIT and MyShell. Audio foundation model.

Use for zero-shot TTS plus speech editing in one model, rather than pure TTS.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Use for a controllable TTS toolkit covering 7000+ languages, though not zero-shot-focused.

Controllable and fast Text-to-Speech for over 7000 languages!

Use for LLM-based audio editing with TTS capability, if editing is the primary need.

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech

Use for an all-in-one speech toolkit with TTS, ASR, and more, if you need broader speech tasks.

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Use for a broad speech-processing framework with TTS recipes, if you want many tools.

End-to-End Speech Processing Toolkit

Use for a production-grade speech framework with TTS/ASR, if you need a full toolkit.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Use for a simple English-oriented local voice cloner, but it's older and narrower.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Use for a battle-tested TTS toolkit, but unmaintained for over 2 years.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Use for prompt-controlled emotional TTS, but no updates in 2 years.

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

Use for an early expressive-TTS foundation model, but stale and superseded.

Foundational model for human-like, expressive TTS

Use for a simple voice-cloning demo with limited language coverage and older architecture.

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time