Kokoro-82M

A cutting-edge text-to-speech (TTS) model with 82 million parameters.

CommonProductMusicText-to-SpeechSpeech Synthesis

Kokoro-82M is a text-to-speech (TTS) model created by hexgrad and hosted on Hugging Face. It features 82 million parameters and is open-sourced under the Apache 2.0 license. The model released version 0.19 on December 25, 2024, offering 10 unique voice packages. Kokoro-82M ranks first in the TTS Spaces Arena, showcasing its efficiency in parameter scale and data usage. It supports both American and British English, making it suitable for generating high-quality speech output.

Best AI Websites & Tools

Kokoro-82M

Kokoro-82M Visit Over Time

Kokoro-82M Visit Trend

Kokoro-82M Visit Geography

Kokoro-82M Traffic Sources

Kokoro-82M Alternatives

Llasa-1B — Llasa-1B is a text-to-speech (TTS) model based on the LLaMA architecture, supporting both Chinese and English speech synthesis.

Llasa-3B — Llasa-3B is a text-to-speech synthesis model based on LLaMA that supports speech generation in both Chinese and English.

OuteTTS-0.2-500M — High-performance text-to-speech synthesis model

OuteTTS — An experimental text-to-speech model.

MaskGCT TTS Demo — Text-to-speech demonstration based on the MaskGCT model.

MaskGCT — Zero-shot text-to-speech conversion model that does not require alignment information.

F5-TTS — A high-quality text-to-speech synthesis model based on deep learning.

VALL-E 2 — A speech synthesis technology developed by Microsoft Research Asia

Bailing-TTS — A large-scale text-to-speech model for generating high-quality Chinese dialect voices.

ToucanTTS — Multilingual controllable text-to-speech synthesis toolkit

Aura TTS Demo by Deepgram — Deepgram's Aura TTS demo showcases advanced speech synthesis technology.

Whisper Speech — Open-source text-to-speech system

StyleTTS 2 — Human-level text-to-speech synthesis model

PIKE-RAG — PIKE-RAG is a model specializing in domain knowledge and reasoning-enhanced generation.

SkyReels-V1-Hunyuan-I2V — SkyReels V1 is an open-source, human-centric video foundation model focused on high-quality, cinematic video generation.

Xingsheng AI — Xingsheng AI is an AI podcast generator that can create AI podcasts from any content.

Huginn-0125 — Huginn-0125 is a latent variable recurrent deep model with 3.5 billion parameters, excelling in inference and code generation.

Zonos — Zonos-v0.1 is a leading open-weight text-to-speech model capable of generating high-quality multilingual speech.

Zonos-v0.1-hybrid — Zonos-v0.1-hybrid is a leading open-source text-to-speech model that delivers high-quality voice synthesis services.

Zonos-v0.1 — Zonos-v0.1 is a real-time text-to-speech (TTS) model featuring high-fidelity voice cloning capabilities.

TurboTTS — TurboTTS is a free online text-to-speech tool that offers high-quality, human-like voice synthesis services.

Hibiki — Hibiki is a model designed for streaming voice translation (i.e., simultaneous interpretation) that can generate accurate translations in real time, chunk by chunk.

Sonofa — Transform webpages, PDFs, or images into engaging podcasts, allowing easy listening anytime, anywhere.

Qwen2.5-1M — An open-source Qwen model supporting a context of 1 million tokens, suitable for long sequence processing tasks.

LLaSA_training — LLaSA: Extending training and inference computational requirements for LLaMA-based speech synthesis

YuE — YuE is an open-source music foundation model focused on generating complete songs based on lyrics.

Kokoro TTS — An advanced AI text-to-speech model based on the StyleTTS 2 architecture, featuring 82 million parameters and delivering high-quality natural speech synthesis.

Hailuo AI Audio — Hailuo AI Audio is an audio synthesis tool designed to create realistic speech.

kokoro-onnx — A text-to-speech (TTS) project based on Kokoro and ONNX runtime.