supertone-inc/supertonic Alternatives

For a similar ONNX-based local TTS with many prebuilt voices; swap if you prefer Piper's model ecosystem.

A fast, local neural text to speech system

For a broader ONNX-based speech toolkit with TTS plus STT/VAD, if you also need other speech features.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

For a tokenizer-free neural TTS with creative voice design and cloning, though not ONNX-based.

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

For a Python-native TTS with high-quality multilingual voices, if you don't need ONNX cross-platform deployment.

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

For an ultra-small CPU TTS in Python, if you need an even lighter model than Supertonic.

A TTS that fits in your CPU (and pocket)

For a modern TTS inference model with multilingual support, but not optimized for on-device ONNX.

Spark-TTS Inference Code

For a full TTS toolkit with training abilities, if you need fine-tuning instead of just inference.

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

For an English/Chinese TTS engine with fine emotion control, if that matters more than ONNX performance.

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

For Apple Silicon native MLX acceleration, if you're only targeting Apple platforms.

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

For cloud-based TTS via Microsoft Edge, if you need zero local resources and are okay with internet.

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

For a state-of-the-art TTS model with speech generation and control, if you can handle heavier compute.

SoTA open-source TTS

For a high-quality multilingual TTS with expressive controls, if ONNX portability isn't needed.

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.

For instant voice cloning on top of TTS, if your primary need is cloning rather than multilingual synthesis.

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

For an industrial-level controllable zero-shot TTS, if you need controllable generation over deployment ease.

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

For a large multilingual voice generation model with full-stack training, if you need that scale.

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

For low-latency STT/TTS/intent in a single model, if you need a combined voice agent toolkit.

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

For voice cloning in 600+ languages, if language coverage and cloning are your priority.

High-Quality Voice Cloning TTS for 600+ Languages

For a classic VITS model if you require the original architecture; it's older and not as fast as modern ONNX TTS.

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

For a zero-shot TTS implementation, but it's archived and older; choose if you need that specific model.

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

For an older, simple voice cloning TTS; choose if you need a lightweight cloning demo, but it's not multilingual.

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

For an end-user graphical UI combining multiple TTS and voice cloning engines, rather than a library.

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.