rany2/edge-tts Alternatives

Choose when you need local voice cloning and style transfer with fast inference; requires PyTorch and model weights.

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

Choose when you want a modern tokenizer-free multilingual TTS with voice cloning; local and GPU-friendly.

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

Choose when you need a controllable, efficient zero-shot TTS for industrial use; local deployment.

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

Choose when you need large-scale multilingual voice generation with full training/deployment stack; local and heavy.

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

Choose when you need high-quality voice cloning for 600+ languages offline; heavier local setup.

High-Quality Voice Cloning TTS for 600+ Languages

Choose when you need TTS that fits on CPU with low latency; much smaller footprint than an online API.

A TTS that fits in your CPU (and pocket)

Choose when you want open-weight, expressive TTS close to top commercial quality; needs GPU.

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 have one minute of voice data and need few-shot voice cloning; local training pipeline.

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

Choose when you want a mature, battle-tested local TTS toolkit with many model choices; stale but works.

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

Choose when you need SoTA local open TTS with naturalness; requires GPU and model download.

SoTA open-source TTS

Choose when you need fully offline TTS alongside ASR/VAD/diarization in an embedded-friendly onnxruntime package.

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

Choose when you want a full PaddlePaddle speech toolkit with TTS, ASR, and more; heavier framework.

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.

Choose when you need a fast offline neural TTS with small footprint for edge; limited voice set.

A fast, local neural text to speech system

Choose when you need a specific Spark-TTS model for local inference; niche spark voice model.

Spark-TTS Inference Code

Choose when you need very low-latency on-device voice (STT/ITN/TTS) for voice agents; not a dedicated TTS.

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

Choose when you are doing research or building custom audio generation and need a flexible toolkit.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

Choose when you need an end-to-end speech processing toolkit for research/training with TTS components.

End-to-End Speech Processing Toolkit

Choose when you need prompt-controlled emotions in a local TTS engine; fewer languages.

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

Choose when you're on Apple Silicon and want MLX-optimized speech; Apple-specific and local.

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.

Choose when you need a lightweight multilingual local TTS library; good for low-resource deployment.

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

Choose when you want a research TTS built by inverting Whisper; local and experimental.

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

Choose when you need a tiny offline formant synthesizer with many languages and minimal resources; robotic quality.

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

Choose when you need a simple offline Python TTS using OS-native engines; no internet, but dated/robotic voices.

Offline Text To Speech synthesis for python