QwenLM/Qwen3-TTS Alternatives

Choose when you need voice cloning TTS for 600+ languages under Apache-2.0.

High-Quality Voice Cloning TTS for 600+ Languages

Choose when you want a strongly expressive open-weight TTS with multilingual support.

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.

Choose when you need extremely fast voice cloning (150x realtime).

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

Choose when you want a broader sound/speech generation family with Apache-2.0.

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

Choose when you need few-shot voice cloning from just 1 minute of audio and MIT license.

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

Choose when you need a full-stack multilingual voice generation toolkit with training and deployment.

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

Choose when you want Spark-TTS's specific zero-shot voice cloning architecture.

Spark-TTS Inference Code

Choose when you need cross-lingual zero-shot TTS with NetEase's engine.

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

Choose when you want lightweight instant voice cloning with tone color transfer under MIT.

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

Choose when you prefer tokenizer-free TTS with creative voice design and true-to-life cloning.

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

Choose when you need an industrial-level controllable zero-shot TTS with efficient inference.

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

Choose when you also need zero-shot speech editing in addition to TTS.

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

Choose when you need controllable TTS for over 7000 languages in a lightweight system.

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

Choose when you want an LLM-empowered TTS with MPL-2.0 licensing.

An Open-Sourced LLM-empowered Foundation TTS System

Choose when you need emotion-expressive zero-shot TTS via multi-reward reinforcement learning.

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

Choose when you prefer a TTS built on inverted Whisper with MIT license.

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

Choose when you want an LLM-based model that edits emotion and style while also performing zero-shot TTS.

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

Previous generation with no recent pushes, but still a valid Apache-2.0 expressive TTS foundation.

Foundational model for human-like, expressive TTS

It's an end-user AI voice studio application, not a library you can embed.

The open-source AI voice studio. Clone, dictate, create.

It's an end-user notebook for Bark-based voice cloning, not an embeddable model.

Bark Voice Cloning and Voice Cloning for Chinese Speech