--- title: "ChatTTS vs CosyVoice" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/2noise-chattts-vs-funaudiollm-cosyvoice" tools: ["2noise-chattts", "funaudiollm-cosyvoice"] --- # ChatTTS vs CosyVoice *GraphCanon updated Aug 23, 2026* ## Verdict Pick ChatTTS if chatTTS is a Python-based repository for generating speech tailored to everyday conversations in both Chinese and English; pick CosyVoice if cosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation. [ChatTTS](https://2noise.com) reports 40k GitHub stars, 4.3k forks, and 60 open issues, last pushed Apr 10, 2026. [CosyVoice](https://funaudiollm.github.io/cosyvoice3) has 23k stars, 2.6k forks, and 719 open issues, last pushed May 25, 2026. Figures are from public GitHub metadata via [ChatTTS's repository](https://github.com/2noise/ChatTTS) and [CosyVoice's repository](https://github.com/FunAudioLLM/CosyVoice). | | [ChatTTS](/tools/2noise-chattts.md) | [CosyVoice](/tools/funaudiollm-cosyvoice.md) | | --- | --- | --- | | Tagline | A generative speech model for daily dialogue | Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment. | | Stars | 39,768 | 22,870 | | Forks | 4,257 | 2,631 | | Open issues | 60 | 719 | | Language | Python | Python | | Adopt for | ChatTTS is a Python-based repository for generating speech tailored to everyday conversations in both Chinese and English. | CosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation. | | Persona | - | - | | Runtime | - | - | | License | Licensed under AGPL-3.0, which allows for free use, distribution, and modification as long as these rights are maintained in derivative works. | Apache-2.0 | | Categories | AI Agents, Speech & Audio | Inference & Serving, Model Training, Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [ChatTTS](/tools/2noise-chattts.md) | [CosyVoice](/tools/funaudiollm-cosyvoice.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Steady (60%) | | Days since push | 127d | 89d | | Open issues (now) | 60 | 719 | | Stars delta | +140 (30d) | +497 (30d) | | Open issues delta | -1 (30d) | -37 (30d) | | Full report | [trust report](/tools/2noise-chattts/trust.md) | [trust report](/tools/funaudiollm-cosyvoice/trust.md) | ## Shared compatibility - **Python**: [ChatTTS](/tools/2noise-chattts.md) - Python runtime; [CosyVoice](/tools/funaudiollm-cosyvoice.md) - Python runtime ## Decision facts: ChatTTS - **Hosting:** unknown - **Requirements:** Python-based implementation means that familiarity with Python is necessary for effective use. - **Adopt for:** ChatTTS is a Python-based repository for generating speech tailored to everyday conversations in both Chinese and English. - **License detail:** Licensed under AGPL-3.0, which allows for free use, distribution, and modification as long as these rights are maintained in derivative works. ## Decision facts: CosyVoice - **Adopt for:** CosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation. ## Choose when ### Choose ChatTTS if… - License: ChatTTS is AGPL-3.0, CosyVoice is Apache-2.0. - Requirements: Python-based implementation means that familiarity with Python is necessary for effective use.. - Tags unique to ChatTTS: agent, chattts, chinese language, english-language. - Also covers AI Agents. - Use ChatTTS when you require text-to-speech functionality for daily dialogue applications, especially those involving Chinese or English languages. ### Choose CosyVoice if… - License: CosyVoice is Apache-2.0, ChatTTS is AGPL-3.0. - Tags unique to CosyVoice: audio-generation, cantonese, chatbot, chinese. - Also covers Inference & Serving, Model Training. - When you need support for multiple languages like Cantonese, Chinese, English, Japanese, and Korean. ## When NOT to use ChatTTS - Avoid using ChatTTS in environments where the speech generation model is expected to handle complex technical jargon or specialized vocabulary, as it's optimized for daily conversation. - Do not use ChatTTS if your project requires the integration of more than two languages simultaneously due to its current support for only Chinese and English. ## When NOT to use CosyVoice - If your project specifically requires fine-tuned performance in languages not supported by CosyVoice such as Arabic or Spanish. - When strict real-time speech synthesis requirements are essential, as CosyVoice may face delays depending on the environment's computational power and model complexity. ## Common questions ### What is the difference between ChatTTS and CosyVoice? ChatTTS: A generative speech model for daily dialogue. CosyVoice: Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment.. See the comparison table for live GitHub stats and shared categories. ### When should I choose ChatTTS over CosyVoice? Choose ChatTTS over CosyVoice when License: ChatTTS is AGPL-3.0, CosyVoice is Apache-2.0; Requirements: Python-based implementation means that familiarity with Python is necessary for effective use.; Tags unique to ChatTTS: agent, chattts, chinese language, english-language; Also covers AI Agents; Use ChatTTS when you require text-to-speech functionality for daily dialogue applications, especially those involving Chinese or English languages. ### When should I choose CosyVoice over ChatTTS? Choose CosyVoice over ChatTTS when License: CosyVoice is Apache-2.0, ChatTTS is AGPL-3.0; Tags unique to CosyVoice: audio-generation, cantonese, chatbot, chinese; Also covers Inference & Serving, Model Training; When you need support for multiple languages like Cantonese, Chinese, English, Japanese, and Korean. ### When should I avoid ChatTTS? Avoid using ChatTTS in environments where the speech generation model is expected to handle complex technical jargon or specialized vocabulary, as it's optimized for daily conversation. Do not use ChatTTS if your project requires the integration of more than two languages simultaneously due to its current support for only Chinese and English. ### When should I avoid CosyVoice? If your project specifically requires fine-tuned performance in languages not supported by CosyVoice such as Arabic or Spanish. When strict real-time speech synthesis requirements are essential, as CosyVoice may face delays depending on the environment's computational power and model complexity. ### Is ChatTTS or CosyVoice more popular on GitHub? ChatTTS has more GitHub stars (39,768 vs 22,870). Stars measure visibility, not whether either tool fits your constraints. ### Are ChatTTS and CosyVoice open source? Yes - both are open-source projects on GitHub (ChatTTS: AGPL-3.0, CosyVoice: Apache-2.0). ### Where can I find alternatives to ChatTTS or CosyVoice? GraphCanon lists graph-backed alternatives at [ChatTTS alternatives](/tools/2noise-chattts/alternatives) and [CosyVoice alternatives](/tools/funaudiollm-cosyvoice/alternatives) ([ChatTTS markdown twin](/tools/2noise-chattts/alternatives.md), [CosyVoice markdown twin](/tools/funaudiollm-cosyvoice/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/2noise-chattts-vs-funaudiollm-cosyvoice.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, ChatTTS or CosyVoice? ChatTTS: Slowing. CosyVoice: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for ChatTTS and CosyVoice? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [ChatTTS trust report](/tools/2noise-chattts/trust); [CosyVoice trust report](/tools/funaudiollm-cosyvoice/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=2noise-chattts`](/api/graphcanon/graph?tool=2noise-chattts) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_