hexgrad/Kokoro-82M

1---2license: apache-2.03language:4- en5base_model:6- yl4579/StyleTTS2-LJSpeech7pipeline_tag: text-to-speech8---9**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.10 11<audio controls><source src="https://huggingface.co/hexgrad/Kokoro-82M/resolve/main/samples/HEARME.wav" type="audio/wav"></audio>12 13🐈 **GitHub**: https://github.com/hexgrad/kokoro14 15🚀 **Demo**: https://hf.co/spaces/hexgrad/Kokoro-TTS16 17> [!NOTE]18> As of April 2025, the market rate of Kokoro served over API is **under $1 per million characters of text input**, or under $0.06 per hour of audio output. (On average, 1000 characters of input is about 1 minute of output.) Sources: [ArtificialAnalysis/Replicate at 65 cents per M chars](https://artificialanalysis.ai/text-to-speech/model-family/kokoro#price) and [DeepInfra at 80 cents per M chars](https://deepinfra.com/hexgrad/Kokoro-82M).19>20> This is an Apache-licensed model, and Kokoro has been deployed in numerous projects and commercial APIs. We welcome the deployment of the model in real use cases.21 22> [!CAUTION]23> Fake websites like kokorottsai_com (snapshot: https://archive.ph/nRRnk) and kokorotts_net (snapshot: https://archive.ph/60opa) are likely scams masquerading under the banner of a popular model.24>25> Any website containing "kokoro" in its root domain (e.g. kokorottsai_com, kokorotts_net) is **NOT owned by and NOT affiliated with this model page or its author**, and attempts to imply otherwise are red flags.26 27- [Releases](#releases)28- [Usage](#usage)29- [EVAL.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/EVAL.md) ↗️30- [SAMPLES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/SAMPLES.md) ↗️31- [VOICES.md](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) ↗️32- [Model Facts](#model-facts)33- [Training Details](#training-details)34- [Creative Commons Attribution](#creative-commons-attribution)35- [Acknowledgements](#acknowledgements)36 37### Releases38 39| Model | Published | Training Data | Langs & Voices | SHA256 |40| ----- | --------- | ------------- | -------------- | ------ |41| **v1.0** | **2025 Jan 27** | **Few hundred hrs** | [**8 & 54**](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | `496dba11` |42| [v0.19](https://huggingface.co/hexgrad/kLegacy/tree/main/v0.19) | 2024 Dec 25 | <100 hrs | 1 & 10 | `3b0c392f` |43 44| Training Costs | v0.19 | v1.0 | **Total** |45| -------------- | ----- | ---- | ----- |46| in A100 80GB GPU hours | 500 | 500 | **1000** |47| average hourly rate | $0.80/h | $1.20/h | **$1/h** |48| in USD | $400 | $600 | **$1000** |49 50### Usage51You can run this basic cell on [Google Colab](https://colab.research.google.com/). [Listen to samples](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/SAMPLES.md). For more languages and details, see [Advanced Usage](https://github.com/hexgrad/kokoro?tab=readme-ov-file#advanced-usage).52```py53!pip install -q kokoro>=0.9.2 soundfile54!apt-get -qq -y install espeak-ng > /dev/null 2>&155from kokoro import KPipeline56from IPython.display import display, Audio57import soundfile as sf58import torch59pipeline = KPipeline(lang_code='a')60text = '''61[Kokoro](/kˈOkəɹO/) 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](/kˈOkəɹO/) can be deployed anywhere from production environments to personal projects.62'''63generator = pipeline(text, voice='af_heart')64for i, (gs, ps, audio) in enumerate(generator):65    print(i, gs, ps)66    display(Audio(data=audio, rate=24000, autoplay=i==0))67    sf.write(f'{i}.wav', audio, 24000)68```69Under the hood, `kokoro` uses [`misaki`](https://pypi.org/project/misaki/), a G2P library at https://github.com/hexgrad/misaki70 71### Model Facts72 73**Architecture:**74- StyleTTS 2: https://arxiv.org/abs/2306.0769175- ISTFTNet: https://arxiv.org/abs/2203.0239576- Decoder only: no diffusion, no encoder release77 78**Architected by:** Li et al @ https://github.com/yl4579/StyleTTS279 80**Trained by**: `@rzvzn` on Discord81 82**Languages:** Multiple83 84**Model SHA256 Hash:** `496dba118d1a58f5f3db2efc88dbdc216e0483fc89fe6e47ee1f2c53f18ad1e4`85 86### Training Details87 88**Data:** Kokoro was trained exclusively on **permissive/non-copyrighted audio data** and IPA phoneme labels. Examples of permissive/non-copyrighted audio include:89- Public domain audio90- Audio licensed under Apache, MIT, etc91- Synthetic audio<sup>[1]</sup> generated by closed<sup>[2]</sup> TTS models from large providers<br/>92[1] https://copyright.gov/ai/ai_policy_guidance.pdf<br/>93[2] No synthetic audio from open TTS models or "custom voice clones"94 95**Total Dataset Size:** A few hundred hours of audio96 97**Total Training Cost:** About $1000 for 1000 hours of A100 80GB vRAM98 99### Creative Commons Attribution100 101The following CC BY audio was part of the dataset used to train Kokoro v1.0.102 103| Audio Data | Duration Used | License | Added to Training Set After |104| ---------- | ------------- | ------- | --------------------------- |105| [Koniwa](https://github.com/koniwa/koniwa) `tnc` | <1h | [CC BY 3.0](https://creativecommons.org/licenses/by/3.0/deed.ja) | v0.19 / 22 Nov 2024 |106| [SIWIS](https://datashare.ed.ac.uk/handle/10283/2353) | <11h | [CC BY 4.0](https://datashare.ed.ac.uk/bitstream/handle/10283/2353/license_text) | v0.19 / 22 Nov 2024 |107 108### Acknowledgements109 110- 🛠️ [@yl4579](https://huggingface.co/yl4579) for architecting StyleTTS 2.111- 🏆 [@Pendrokar](https://huggingface.co/Pendrokar) for adding Kokoro as a contender in the TTS Spaces Arena.112- 📊 Thank you to everyone who contributed synthetic training data.113- ❤️ Special thanks to all compute sponsors.114- 👾 Discord server: https://discord.gg/QuGxSWBfQy115- 🪽 Kokoro is a Japanese word that translates to "heart" or "spirit". It is also the name of an [AI in the Terminator franchise](https://terminator.fandom.com/wiki/Kokoro).116 117<img src="https://static0.gamerantimages.com/wordpress/wp-content/uploads/2024/08/terminator-zero-41-1.jpg" width="400" alt="kokoro" />118