Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text to speech

kokoro-82m-onnx-webgpu-nostft

by Jeremie Strand skillsafeai/kokoro-82m-onnx-webgpu-nostft

kokoro-82m-onnx-webgpu-nostft is an open-weight model for text to speech from Jeremie Strand, released under Apache License 2.0. Its published files total 325.5 MB.

The fp32 onnx/model.onnx from onnx-community/Kokoro-82M-v1.0-ONNX at revision 1939ad2a, with the graph cut at decoder.generator.convpost. The weights are unchanged.

Parameters—
Context—
Weights325.5 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Jeremie Strand, published under apache-2.0, revision 685f3d1a9015.

The fp32 onnx/model.onnx from onnx-community/Kokoro-82M-v1.0-ONNX at revision 1939ad2a, with the graph cut at decoder.generator.convpost. The weights are unchanged. Why: on onnxruntime-web 1.27 WebGPU, the full graph's iSTFT tail (ConvTranspose/ScatterND) returns zeros for every sample past about 65,528 (2.7 s at 24 kHz). Callers then have to feed short phrases, and that audibly flattens the prosody. Inputs: inputids int64 [1, n], style float32 [1, 256], speed float32 [1] (same as upstream). iSTFT to run in the caller (nfft 20, hop 5; istftbasis.json = the 22x20 inverse basis): This matches the full graph's waveform to within 6e-7 (max abs, CPU). Kokoro-82M is by hexgrad, released under…

Read Jeremie Strand's full model card

Kokoro-82M, fp32 ONNX cut before the iSTFT (for onnxruntime-web WebGPU)

The fp32 onnx/model.onnx from onnx-community/Kokoro-82M-v1.0-ONNX at revision 1939ad2a, with the graph cut at decoder.generator.conv_post. The weights are unchanged.

Why: on onnxruntime-web 1.27 WebGPU, the full graph's iSTFT tail (ConvTranspose/ScatterND) returns zeros for every sample past about 65,528 (2.7 s at 24 kHz). Callers then have to feed short phrases, and that audibly flattens the prosody.

Inputs: input_ids int64 [1, n], style float32 [1, 256], speed float32 [1] (same as upstream). Output: spec_phase float32 [1, 22, frames].

iSTFT to run in the caller (n_fft 20, hop 5; istft_basis.json = the 22x20 inverse basis):

mag = exp(x[0:11]); ph = sin(x[11:22]); c = concat(mag*cos(ph), mag*sin(ph))   # 22 x F
y = conv_transpose1d(c, basis[22,1,20], stride=5)                               # 5(F-1)+20
y[1:20] /= window_sum[1:20]        # as exported: only the first window is normalised
waveform = 4 * y[10:-10]

This matches the full graph's waveform to within 6e-7 (max abs, CPU). Kokoro-82M is by hexgrad, released under Apache-2.0.

Identity and Version

Repository
skillsafeai/kokoro-82m-onnx-webgpu-nostft
Publisher
Jeremie Strand
Task
Text to speech
Modality
Audio
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
685f3d1a9015b6c1ce7fbe7ace7c32b47f594519
First published
2026-09-24
Last updated
2026-09-24

Files and Weights

4 files, 325.5 MB in total. The weights are 1 file totalling 325.5 MB in onnx.

Weights1 file · 325.5 MB
Configuration1 file · 9.4 KB
Documentation1 file · 1.3 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
kokoro_body.onnxWeights325.5 MB 94fd4b69a4a0
istft_basis.jsonConfiguration9.4 KB —
README.mdDocumentation1.3 KB —
.gitattributesRepository1.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
325.5 MB
Download from Jeremie Strand

Released by Jeremie Strand through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published325.5 MB

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

Questions About kokoro-82m-onnx-webgpu-nostft

Can I use kokoro-82m-onnx-webgpu-nostft commercially?

Yes. kokoro-82m-onnx-webgpu-nostft 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

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

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

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