{"name":"Chatterbox: State-of-the-Art Open-Source Text-to-Speech by Resemble AI","description":"Chatterbox is a powerful family of open-source text-to-speech (TTS) models developed by Resemble AI, designed for high-quality speech generation. It features Chatterbox-Turbo, an efficient model with paralinguistic tags for added realism, alongside multilingual and general-purpose TTS options. These models provide robust solutions for voice agents, narration, and creative workflows, incorporating responsible AI features like built-in watermarking.","github":"https://github.com/resemble-ai/chatterbox","url":"https://osrepos.com/repo/resemble-ai-chatterbox","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/resemble-ai-chatterbox","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/resemble-ai-chatterbox.md","json":"https://osrepos.com/repo/resemble-ai-chatterbox.json","topics":["Python","Text-to-Speech","TTS","AI","Machine Learning","Open Source","Speech Synthesis","Voice Cloning"],"keywords":["Python","Text-to-Speech","TTS","AI","Machine Learning","Open Source","Speech Synthesis","Voice Cloning"],"stars":null,"summary":"Chatterbox is a powerful family of open-source text-to-speech (TTS) models developed by Resemble AI, designed for high-quality speech generation. It features Chatterbox-Turbo, an efficient model with paralinguistic tags for added realism, alongside multilingual and general-purpose TTS options. These models provide robust solutions for voice agents, narration, and creative workflows, incorporating responsible AI features like built-in watermarking.","content":"## Introduction\nChatterbox is a collection of state-of-the-art, open-source text-to-speech (TTS) models developed by Resemble AI. This family of models offers high-fidelity speech generation, catering to various applications from real-time voice agents to creative content creation.\n\nThe latest addition, **Chatterbox-Turbo**, stands out as Resemble AI's most efficient model to date. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with significantly less compute and VRAM compared to its predecessors. A key innovation is the distillation of the speech-token-to-mel decoder, reducing generation from 10 steps to just one, while maintaining exceptional audio fidelity. Chatterbox-Turbo also natively supports paralinguistic tags, allowing users to integrate realistic elements like `[cough]`, `[laugh]`, and `[chuckle]` into generated speech. While optimized for low-latency voice agents, Turbo also excels in narration and diverse creative workflows.\n\nThe Chatterbox family also includes a Multilingual model supporting over 23 languages for global applications and localization, and the original Chatterbox model offering creative controls like CFG and exaggeration tuning.\n\n## Installation\nYou can easily install Chatterbox using pip:\nshell\npip install chatterbox-tts\n\n\nAlternatively, you can install from source for more control:\nshell\n# conda create -yn chatterbox python=3.11\n# conda activate chatterbox\n\ngit clone https://github.com/resemble-ai/chatterbox.git\ncd chatterbox\npip install -e .\n\nChatterbox was developed and tested on Python 3.11 on Debian 11 OS, with dependencies pinned for consistency.\n\n## Examples\nHere are examples demonstrating how to use the Chatterbox models for speech generation.\n\n### Chatterbox-Turbo\npython\nimport torchaudio as ta\nimport torch\nfrom chatterbox.tts_turbo import ChatterboxTurboTTS\n\n# Load the Turbo model\nmodel = ChatterboxTurboTTS.from_pretrained(device=\"cuda\")\n\n# Generate with Paralinguistic Tags\ntext = \"Hi there, Sarah here from MochaFone calling you back [chuckle], have you got one minute to chat about the billing issue?\"\n\n# Generate audio (requires a reference clip for voice cloning)\nwav = model.generate(text, audio_prompt_path=\"your_10s_ref_clip.wav\")\n\nta.save(\"test-turbo.wav\", wav, model.sr)\n\n\n### Chatterbox and Chatterbox-Multilingual\npython\n\nimport torchaudio as ta\nfrom chatterbox.tts import ChatterboxTTS\nfrom chatterbox.mtl_tts import ChatterboxMultilingualTTS\n\n# English example\nmodel = ChatterboxTTS.from_pretrained(device=\"cuda\")\n\ntext = \"Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill.\"\nwav = model.generate(text)\nta.save(\"test-english.wav\", wav, model.sr)\n\n# Multilingual examples\nmultilingual_model = ChatterboxMultilingualTTS.from_pretrained(device=device)\n\nfrench_text = \"Bonjour, comment ça va? Ceci est le modèle de synthèse vocale multilingue Chatterbox, il prend en charge 23 langues.\"\nwav_french = multilingual_model.generate(french_text, language_id=\"fr\")\nta.save(\"test-french.wav\", wav_french, model.sr)\n\nchinese_text = \"???????????????????????\"\nwav_chinese = multilingual_model.generate(chinese_text, language_id=\"zh\")\nta.save(\"test-chinese.wav\", wav_chinese, model.sr)\n\n# If you want to synthesize with a different voice, specify the audio prompt\nAUDIO_PROMPT_PATH = \"YOUR_FILE.wav\"\nwav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH)\nta.save(\"test-2.wav\", wav, model.sr)\n\n\n## Why Use Chatterbox?\nChatterbox offers a compelling solution for text-to-speech needs due to several key advantages:\n\n*   **State-of-the-Art Performance:** Delivers high-quality, natural-sounding speech across its model family.\n*   **Exceptional Efficiency:** Chatterbox-Turbo provides significant performance gains, reducing compute and VRAM requirements while speeding up generation to a single step.\n*   **Realistic Paralinguistic Tags:** Enhance expressiveness and realism in generated audio with built-in tags like laughs and chuckles.\n*   **Broad Multilingual Support:** The Multilingual model supports over 23 languages, making it suitable for global applications and diverse content.\n*   **Voice Cloning Capabilities:** Easily generate speech in different voices by providing an audio prompt.\n*   **Responsible AI:** Integrates Resemble AI's PerTh (Perceptual Threshold) Watermarker, embedding imperceptible neural watermarks for ethical AI use.\n*   **Active Community:** Join the official Discord for support and collaboration.\n\n## Links\n*   **GitHub Repository:** [https://github.com/resemble-ai/chatterbox](https://github.com/resemble-ai/chatterbox)\n*   **Chatterbox-Turbo Demo Samples:** [https://resemble-ai.github.io/chatterbox_turbo_demopage/](https://resemble-ai.github.io/chatterbox_turbo_demopage/)\n*   **Chatterbox-Turbo Hugging Face Space:** [https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo)\n*   **Official Discord:** [https://discord.gg/rJq9cRJBJ6](https://discord.gg/rJq9cRJBJ6)\n*   **Resemble AI (for commercial scaling/tuning):** [https://resemble.ai](https://resemble.ai)","metrics":{"detailViews":8,"githubClicks":8},"dates":{"published":null,"modified":"2026-04-19T12:56:33.000Z"}}