SAVRN
Search Contact SAVRN

Open-weight model · Text to speech

Kokoro-82M-bf16

by MLX Community mlx-community/Kokoro-82M-bf16

This model was converted to MLX format from hexagrad/Kokoro-82M using mlx-audio version 0.0.1. Refer to the original model card for more details on the model.

Parameters—
Context—
Weights383.6 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads87.2k

Model Card

By MLX Community, published under apache-2.0, revision a71e4d38b236.

This model was converted to MLX format from hexagrad/Kokoro-82M using mlx-audio version 0.0.1. Refer to the original model card for more details on the model.

Read MLX Community's full model card

This model was converted to MLX format from hexagrad/Kokoro-82M using mlx-audio version 0.0.1. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-audio

python -m mlx_audio.tts.generate --model mlx-community/Kokoro-82M-bf16 --text "Hello world"

Identity and Version

Repository
mlx-community/Kokoro-82M-bf16
Publisher
MLX Community
Task
Text to speech
Modality
Audio
Library
mlx
Parameters
Not stated by the source
Languages
en
Revision
a71e4d38b236d968966a2002c4c895dbd12b1c3c
First published
2025-02-28
Last updated
2025-12-02

Files and Weights

122 files, 389.4 MB in total. The weights are 109 files totalling 383.6 MB in pt, safetensors.

Weights109 files · 383.6 MB
Configuration1 file · 2.4 KB
Documentation4 files · 16.7 KB
Other7 files · 5.8 MB
Repository1 file · 1.9 KB
Every file
FileTypeSizeSHA-256
kokoro-v1_0.safetensorsWeights327.1 MB 4e9ecdf03b8b
voices/af_alloy.ptWeights523.4 KB 6d877149dd8b
voices/af_alloy.safetensorsWeights522.3 KB 5bb848d02ade
voices/af_aoede.ptWeights523.4 KB c03bd1a4c371
voices/af_aoede.safetensorsWeights522.3 KB 23809148777f
voices/af_bella.ptWeights523.4 KB 8cb64e02fcc8
voices/af_bella.safetensorsWeights522.3 KB 112d310468cb
voices/af_heart.ptWeights523.4 KB 0ab5709b8ffa
voices/af_heart.safetensorsWeights522.3 KB 2c1c733b0e65
voices/af_jessica.ptWeights523.4 KB cdfdccb8cc97
voices/af_jessica.safetensorsWeights522.3 KB c358448e4277
voices/af_kore.ptWeights523.4 KB 8bfbc512321c
voices/af_kore.safetensorsWeights522.3 KB c491174280cb
voices/af_nicole.ptWeights523.4 KB c5561808bcf5
voices/af_nicole.safetensorsWeights522.3 KB 574656386022
voices/af_nova.ptWeights523.4 KB e0233676ddc2
voices/af_nova.safetensorsWeights522.3 KB 242b9a0a01ea
voices/af_river.ptWeights523.4 KB e149459bd9c0
voices/af_river.safetensorsWeights522.3 KB 82c866b0b976
voices/af_sarah.ptWeights523.4 KB 49bd364ea3be
voices/af_sarah.safetensorsWeights522.3 KB 494007218254
voices/af_sky.ptWeights523.4 KB c799548aed06
voices/af_sky.safetensorsWeights522.3 KB 957af332330d
voices/am_adam.ptWeights523.4 KB ced7e284aba1
voices/am_adam.safetensorsWeights522.3 KB a4f60a3b9c20
voices/am_echo.ptWeights523.4 KB 8bcfdc852bc9
voices/am_echo.safetensorsWeights522.3 KB 031fc608a900
voices/am_eric.ptWeights523.4 KB ada66f0eefff
voices/am_eric.safetensorsWeights522.3 KB 1fb4a61dcee1
voices/am_fenrir.ptWeights523.4 KB 98e507eca1db
voices/am_fenrir.safetensorsWeights522.3 KB 9abed964b906
voices/am_liam.ptWeights523.4 KB c82550757ddb
voices/am_liam.safetensorsWeights522.3 KB 66b65a96e16c
voices/am_michael.ptWeights523.4 KB 9a443b79a4b2
voices/am_michael.safetensorsWeights522.3 KB 3940147ded35
voices/am_onyx.ptWeights523.4 KB e8452be16cd0
voices/am_onyx.safetensorsWeights522.3 KB b5d6132a5747
voices/am_puck.ptWeights523.4 KB dd1d8973f4ce
voices/am_puck.safetensorsWeights522.3 KB 9a8c2e56413b
voices/am_santa.ptWeights523.4 KB 7f2f7582fa2b
voices/am_santa.safetensorsWeights522.3 KB d1f433b57ffc
voices/bf_alice.ptWeights523.4 KB d292651b6af6
voices/bf_alice.safetensorsWeights522.3 KB 9c77e390d93d
voices/bf_emma.ptWeights523.4 KB d0a423deabf4
voices/bf_emma.safetensorsWeights522.3 KB 8878a75a6661
voices/bf_isabella.ptWeights523.4 KB cdd4c3700380
voices/bf_isabella.safetensorsWeights522.3 KB f7b6076f0256
voices/bf_lily.ptWeights523.4 KB 6e09c2e481e2
voices/bf_lily.safetensorsWeights522.3 KB ee77a419046a
voices/bm_daniel.ptWeights523.4 KB fc3fce4e9c12
voices/bm_daniel.safetensorsWeights522.3 KB b195dec592ee
voices/bm_fable.ptWeights523.4 KB d44935f31352
voices/bm_fable.safetensorsWeights522.3 KB 9fa80184e96d
voices/bm_george.ptWeights523.4 KB f1bc812213dc
voices/bm_george.safetensorsWeights522.3 KB a3d9b8995cbb
voices/bm_lewis.ptWeights523.4 KB b5204750dcba
voices/bm_lewis.safetensorsWeights522.3 KB e1e68013c21a
voices/ef_dora.ptWeights523.4 KB d9d69b0f8a2b
voices/ef_dora.safetensorsWeights522.3 KB 13f6dfe8a498
voices/em_alex.ptWeights523.4 KB 5eac53f767c3
voices/em_alex.safetensorsWeights522.3 KB e3bc4bf56ab4
voices/em_santa.ptWeights523.4 KB aa8620cb96ce
voices/em_santa.safetensorsWeights522.3 KB 37c44211b77b
voices/ff_siwis.ptWeights523.4 KB 8073bf2d2c4b
voices/ff_siwis.safetensorsWeights522.3 KB 5c659c9b9e12
voices/hf_alpha.ptWeights523.4 KB 06906fe05746
voices/hf_alpha.safetensorsWeights522.3 KB e93355a43e6f
voices/hf_beta.ptWeights523.4 KB 63c0a1a6272e
voices/hf_beta.safetensorsWeights522.3 KB 976ea52ba7ed
voices/hm_omega.ptWeights523.4 KB b55f02a8e848
voices/hm_omega.safetensorsWeights522.3 KB 227f0c710d11
voices/hm_psi.ptWeights523.4 KB 2f0f055cea4f
voices/hm_psi.safetensorsWeights522.3 KB 03efb26b99e7
voices/if_sara.ptWeights523.4 KB 6c0b253b955f
voices/if_sara.safetensorsWeights522.3 KB 2f3d092c8ba1
voices/im_nicola.ptWeights523.3 KB 234ed0664864
voices/im_nicola.safetensorsWeights522.3 KB 96b62f7d25c3
voices/jf_alpha.ptWeights523.4 KB 1bf4c9dc69e4
voices/jf_alpha.safetensorsWeights522.3 KB 455f78a6ebe6
voices/jf_gongitsune.ptWeights523.4 KB 1b171917f18f
voices/jf_gongitsune.safetensorsWeights522.3 KB 30d744337db7
voices/jf_nezumi.ptWeights523.4 KB d83f007a7f01
voices/jf_nezumi.safetensorsWeights522.3 KB 65743c88fa1c
voices/jf_tebukuro.ptWeights523.4 KB 0d6917904438
voices/jf_tebukuro.safetensorsWeights522.3 KB 0cc28d928ce1
voices/jm_kumo.ptWeights523.4 KB 98340afd68b1
voices/jm_kumo.safetensorsWeights522.3 KB 9f6b9d85ae09
voices/pf_dora.ptWeights523.4 KB 07e4ff987c5d
voices/pf_dora.safetensorsWeights522.3 KB 9a8d587d60d0
voices/pm_alex.ptWeights523.4 KB cf0ba8c573c2
voices/pm_alex.safetensorsWeights522.3 KB bec864eaeb05
voices/pm_santa.ptWeights523.4 KB d42103169c5c
voices/pm_santa.safetensorsWeights522.3 KB 5009747fd938
voices/zf_xiaobei.ptWeights523.4 KB 9b76be63dab4
voices/zf_xiaobei.safetensorsWeights522.3 KB cbda378bbe26
voices/zf_xiaoni.ptWeights523.4 KB 95b49f169bf1
voices/zf_xiaoni.safetensorsWeights522.3 KB ef37a82850e1
voices/zf_xiaoxiao.ptWeights523.4 KB cfaf6f2ded1e
voices/zf_xiaoxiao.safetensorsWeights522.3 KB cf507ad2319c
voices/zf_xiaoyi.ptWeights523.4 KB b5235dbaeef8
voices/zf_xiaoyi.safetensorsWeights522.3 KB 1f2b7ce315a8
voices/zm_yunjian.ptWeights523.4 KB 76cbf8bad359
voices/zm_yunjian.safetensorsWeights522.3 KB a08940c5dd3d
voices/zm_yunxi.ptWeights523.4 KB dbe6e1ce7c3d
voices/zm_yunxi.safetensorsWeights522.3 KB 78d8bb5ba4a2
voices/zm_yunxia.ptWeights523.4 KB bb2b03b08e84
voices/zm_yunxia.safetensorsWeights522.3 KB 59a4ba431ffa
voices/zm_yunyang.ptWeights523.4 KB 5238ac22e0c7
voices/zm_yunyang.safetensorsWeights522.3 KB 8ad45c1077ab
config.jsonConfiguration2.4 KB —
DONATE.mdDocumentation2.6 KB —
README.mdDocumentation536 B —
SAMPLES.mdDocumentation6.0 KB —
VOICES.mdDocumentation7.6 KB —
samples/HEARME.wavOther996.0 KB aad38e96fa60
samples/af_heart_0.wavOther237.6 KB dd7999ebbc83
samples/af_heart_1.wavOther517.2 KB 2fe4f363b785
samples/af_heart_2.wavOther496.8 KB 68ee75b2d503
samples/af_heart_3.wavOther1.4 MB e758efcd852e
samples/af_heart_4.wavOther1.1 MB d50c90f44768
samples/af_heart_5.wavOther1.0 MB bc4515b9479c
.gitattributesRepository1.9 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
383.6 MB
Download from MLX Community

Released by MLX Community through its official repository on Hugging Face. Read the license.

Built From

  • Derived from yl4579/StyleTTS2-LJSpeech

Memory Requirements

PrecisionWeights in memory
As published383.6 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Kokoro-82M-bf16

Can I use Kokoro-82M-bf16 commercially?

Yes. Kokoro-82M-bf16 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text to speech

Kokoro-82M

Hexgrad

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. You can run this basic cell on Google Colab. Listen to samples. For more languages and details, see Advanced Usage. Under the hood, kokoro uses misaki, a G2P library at https://github.com/hexgrad/misaki Model SHA256 Hash: 496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4 Data: Kokoro was trained exclusively on permissive/non-copyrighted audio data and IPA…

Open weights apache-2.0
View model

Model · Text to speech

XTTS-v2

Coqui.ai

ⓍTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. There is no need for an excessive amount of training data that spans countless hours. This is the same or similar model to what powers Coqui Studio and Coqui API. - Supports 17 languages. - Voice cloning with just a 6-second audio clip. - Emotion and style transfer by cloning. - Cross-language voice cloning. - Multi-lingual speech generation. - 24khz sampling rate. - 2 new languages; Hungarian and Korean - Architectural improvements for speaker conditioning. - Enables the use of multiple speaker references and interpolation between speakers. - Stability…

Open weights other coqui
View model

Model · Text to speech

audio.cpp-gguf

Audio.cpp

This directory contains audio.cpp-native GGUF conversions of multiple speech models. These files are intended for use with audio.cpp. If you enjoy the project, please star audio.cpp on GitHub and this Hugging Face repository. For conversion details, supported layouts, direct-file loading, sidecar embedding, and the latest compatibility notes, see the audio.cpp GGUF guide: - https://github.com/0xShug0/audio.cpp/blob/main/docs/gguf.md!!! Converted and quantized packages are checked with automated metrics, but perceived quality can still differ for human listeners. Please validate the exact package, backend, and route to confirm the output is acceptable for your use case. The table lists the…

Open weights other audio.cpp
View model

Model · Text to speech

chatterbox

Resemble AI

Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages. V3 is designed for broad language coverage like V2, but with stronger stability and more expressive generation. It is the recommended multilingual model for users who want one voice cloning model that works across many languages. Try it in the Chatterbox Multilingual TTS V3 Space. Alongside V3, we are releasing the Single Language Pack: dedicated finetunes for priority languages where tighter quality control, stronger…

Open weights mit chatterbox
View model

Model · Text to speech

F5-TTS

Yushen CHEN

Download F5-TTS or E2 TTS and place under ckpts/ Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

Open weights cc-by-nc-4.0 f5-tts
View model

Model · Text to speech

Kokoro-82M-v1.0-ONNX

ONNX Community

Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out). First, install the kokoro-js library from NPM using: You can then generate speech as follows: Optionally, save the audio to a file: The model is resilient to quantization, enabling efficient high-quality speech synthesis at a fraction of the original model size.

Open weights apache-2.0 transformers.js
View model