[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71920":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},71920,"KittenTTS","KittenML\u002FKittenTTS","KittenML"," State-of-the-art TTS model under 25MB 😻 ","",null,"Python",14072,772,123,81,0,18,45,186,54,43.66,"Apache License 2.0",false,"main",[],"2026-06-12 02:02:56","# Kitten TTS\n\n\u003Cp align=\"center\">\n  \u003Cimg width=\"607\" height=\"255\" alt=\"Kitten TTS\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Ff4646722-ba78-4b25-8a65-81bacee0d4f6\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FKittenML\u002FKittenTTS-Demo\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDemo-Hugging%20Face%20Spaces-orange\" alt=\"Hugging Face Demo\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002FVJ86W4SURW\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Community-5865F2?logo=discord&logoColor=white\" alt=\"Discord\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fkittenml.com\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWebsite-kittenml.com-blue\" alt=\"Website\">\u003C\u002Fa>\n  \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache_2.0-green.svg\" alt=\"License\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n> **New:** Kitten TTS v0.8 is out -- 15M, 40M, and 80M parameter models now available.\n\nKitten TTS is an open-source, lightweight text-to-speech library built on ONNX. With models ranging from 15M to 80M parameters (25-80 MB on disk), it delivers high-quality voice synthesis on CPU without requiring a GPU.\n\n> **Status:** Developer preview -- APIs may change between releases.\n\n**Commercial support is available.** For integration assistance, custom voices, or enterprise licensing, [contact us](https:\u002F\u002Fdocs.google.com\u002Fforms\u002Fd\u002Fe\u002F1FAIpQLSc49erSr7jmh3H2yeqH4oZyRRuXm0ROuQdOgWguTzx6SMdUnQ\u002Fviewform?usp=preview).\n\n## Table of Contents\n\n- [Features](#features)\n- [Available Models](#available-models)\n- [Demo](#demo)\n- [Quick Start](#quick-start)\n- [API Reference](#api-reference)\n- [System Requirements](#system-requirements)\n- [Roadmap](#roadmap)\n- [Commercial Support](#commercial-support)\n- [Community and Support](#community-and-support)\n- [License](#license)\n\n## Features\n\n- **Ultra-lightweight** -- Model sizes from 25 MB (int8) to 80 MB, suitable for edge deployment\n- **CPU-optimized** -- ONNX-based inference runs efficiently without a GPU\n- **8 built-in voices** -- Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, and Leo\n- **Adjustable speech speed** -- Control playback rate via the `speed` parameter\n- **Text preprocessing** -- Built-in pipeline handles numbers, currencies, units, and more\n- **24 kHz output** -- High-quality audio at a standard sample rate\n\n## Available Models\n\n| Model | Parameters | Size | Download |\n|---|---|---|---|\n| kitten-tts-mini | 80M | 80 MB | [KittenML\u002Fkitten-tts-mini-0.8](https:\u002F\u002Fhuggingface.co\u002FKittenML\u002Fkitten-tts-mini-0.8) |\n| kitten-tts-micro | 40M | 41 MB | [KittenML\u002Fkitten-tts-micro-0.8](https:\u002F\u002Fhuggingface.co\u002FKittenML\u002Fkitten-tts-micro-0.8) |\n| kitten-tts-nano | 15M | 56 MB | [KittenML\u002Fkitten-tts-nano-0.8](https:\u002F\u002Fhuggingface.co\u002FKittenML\u002Fkitten-tts-nano-0.8-fp32) |\n| kitten-tts-nano (int8) | 15M | 25 MB | [KittenML\u002Fkitten-tts-nano-0.8-int8](https:\u002F\u002Fhuggingface.co\u002FKittenML\u002Fkitten-tts-nano-0.8-int8) |\n\n> **Note:** Some users have reported issues with the `kitten-tts-nano-0.8-int8` model. If you encounter problems, please [open an issue](https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Fissues).\n\n## Demo\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fd80120f2-c751-407e-a166-068dd1dd9e8d\n\n### Try it online\n\nTry Kitten TTS directly in your browser on [Hugging Face Spaces](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FKittenML\u002FKittenTTS-Demo).\n\n## Quick Start\n\n### Prerequisites\n\n- Python 3.8 or later\n- pip\n\n### Installation\n\n```bash\npip install https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Freleases\u002Fdownload\u002F0.8.1\u002Fkittentts-0.8.1-py3-none-any.whl\n```\n\n### Basic Usage\n\n```python\nfrom kittentts import KittenTTS\n\nmodel = KittenTTS(\"KittenML\u002Fkitten-tts-mini-0.8\")\naudio = model.generate(\"This high-quality TTS model runs without a GPU.\", voice=\"Jasper\")\n\nimport soundfile as sf\nsf.write(\"output.wav\", audio, 24000)\n```\n\n### Advanced Usage\n\n```python\n# Adjust speech speed (default: 1.0)\naudio = model.generate(\"Hello, world.\", voice=\"Luna\", speed=1.2)\n\n# Save directly to a file\nmodel.generate_to_file(\"Hello, world.\", \"output.wav\", voice=\"Bruno\", speed=0.9)\n\n# List available voices\nprint(model.available_voices)\n# ['Bella', 'Jasper', 'Luna', 'Bruno', 'Rosie', 'Hugo', 'Kiki', 'Leo']\n```\n\n### Using with GPU\n\n```\npip install -r requirements_gpu.txt\n```\n\n```python\nm = KittenTTS(\"KittenML\u002Fkitten-tts-mini-0.8\", backend=\"cuda\")\n```\n\nCheck out `example_cuda.py` \n\n## API Reference\n\n### `KittenTTS(model_name, cache_dir=None)`\n\nLoad a model from Hugging Face Hub.\n\n| Parameter | Type | Default | Description |\n|---|---|---|---|\n| `model_name` | `str` | `\"KittenML\u002Fkitten-tts-nano-0.8\"` | Hugging Face repository ID |\n| `cache_dir` | `str` | `None` | Local directory for caching downloaded model files |\n\n### `model.generate(text, voice, speed, clean_text)`\n\nSynthesize speech from text, returning a NumPy array of audio samples at 24 kHz.\n\n| Parameter | Type | Default | Description |\n|---|---|---|---|\n| `text` | `str` | -- | Input text to synthesize |\n| `voice` | `str` | `\"expr-voice-5-m\"` | Voice name (see available voices) |\n| `speed` | `float` | `1.0` | Speech speed multiplier |\n| `clean_text` | `bool` | `False` | Preprocess text (expand numbers, currencies, etc.) |\n\n### `model.generate_to_file(text, output_path, voice, speed, sample_rate, clean_text)`\n\nSynthesize speech and write directly to an audio file.\n\n| Parameter | Type | Default | Description |\n|---|---|---|---|\n| `text` | `str` | -- | Input text to synthesize |\n| `output_path` | `str` | -- | Path to save the audio file |\n| `voice` | `str` | `\"expr-voice-5-m\"` | Voice name |\n| `speed` | `float` | `1.0` | Speech speed multiplier |\n| `sample_rate` | `int` | `24000` | Audio sample rate in Hz |\n| `clean_text` | `bool` | `True` | Preprocess text (expand numbers, currencies, etc.) |\n\n### `normalize_text(text, locale=\"en-US\", return_spans=False)`\n\nNormalize text for TTS without generating audio.\n\n```python\nfrom kittentts import normalize_text\n\nnormalized = normalize_text(\"Dr. Rivera paid $12.50 at 3:05 p.m.\")\n# \"Doctor Rivera paid twelve dollars and fifty cents at three oh five p m.\"\n\nresult = normalize_text(\"Fig. 2\", return_spans=True)\nprint(result.text)\nprint(result.spans)\n```\n\nWhen `return_spans=True`, the result includes original-to-normalized character spans for changed segments such as abbreviations, dates, times, numbers, currency, URLs, and punctuation.\n\n### `model.available_voices`\n\nReturns a list of available voice names: `['Bella', 'Jasper', 'Luna', 'Bruno', 'Rosie', 'Hugo', 'Kiki', 'Leo']`\n\n## System Requirements\n\n- **Operating system:** Linux, macOS, or Windows\n- **Python:** 3.8 or later\n- **Hardware:** Runs on CPU; no GPU required\n- **Disk space:** 25-80 MB depending on model variant\n\nA virtual environment (conda, venv, or similar) is recommended to avoid dependency conflicts.\n\n## Roadmap\n\n- [ ] Release optimized inference engine\n- [ ] Release mobile SDK\n- [ ] Release higher quality TTS models\n- [ ] Release multilingual TTS\n- [ ] Release KittenASR\n- [ ] Need anything else? [Let us know](https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Fissues)\n\n## Commercial Support\n\nWe offer commercial support for teams integrating Kitten TTS into their products. This includes integration assistance, custom voice development, and enterprise licensing.\n\n[Contact us](https:\u002F\u002Fdocs.google.com\u002Fforms\u002Fd\u002Fe\u002F1FAIpQLSc49erSr7jmh3H2yeqH4oZyRRuXm0ROuQdOgWguTzx6SMdUnQ\u002Fviewform?usp=preview) or email info@stellonlabs.com to discuss your requirements.\n\n## Community and Support\n\n- **Discord:** [Join the community](https:\u002F\u002Fdiscord.com\u002Finvite\u002FVJ86W4SURW)\n- **Website:** [kittenml.com](https:\u002F\u002Fkittenml.com)\n- **Custom support:** [Request form](https:\u002F\u002Fdocs.google.com\u002Fforms\u002Fd\u002Fe\u002F1FAIpQLSc49erSr7jmh3H2yeqH4oZyRRuXm0ROuQdOgWguTzx6SMdUnQ\u002Fviewform?usp=preview)\n- **Email:** info@stellonlabs.com\n- **Issues:** [GitHub Issues](https:\u002F\u002Fgithub.com\u002FKittenML\u002FKittenTTS\u002Fissues)\n\n## License\n\nThis project is licensed under the [Apache License 2.0](LICENSE).\n","KittenTTS 是一个轻量级的文本转语音库，模型大小从25MB到80MB不等。该项目基于ONNX构建，能够在CPU上高效运行而无需GPU支持，提供高质量的语音合成。它具备超轻量化、CPU优化、内置8种声音选择以及可调节语速等核心功能。适用于边缘计算设备或对资源有限制但需要高质量语音输出的应用场景。",2,"2026-06-11 03:39:28","high_star"]