--- title: "CosyVoice vs chatterbox-tts-api" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/funaudiollm-cosyvoice-vs-travisvn-chatterbox-tts-api" tools: ["funaudiollm-cosyvoice", "travisvn-chatterbox-tts-api"] --- # CosyVoice vs chatterbox-tts-api *GraphCanon updated Aug 23, 2026* ## Verdict 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; pick chatterbox-tts-api if chatterbox-TTS-API is a locally hosted Python-based text-to-speech API with capabilities similar to ElevenLabs, offering an OpenAI-compatible interface for generating voice-cloned speech. [CosyVoice](https://funaudiollm.github.io/cosyvoice3) reports 23k GitHub stars, 2.6k forks, and 719 open issues, last pushed May 25, 2026. [chatterbox-tts-api](https://chatterboxtts.com) has 666 stars, 152 forks, and 16 open issues, last pushed Dec 23, 2025. Figures are from public GitHub metadata via [CosyVoice's repository](https://github.com/FunAudioLLM/CosyVoice) and [chatterbox-tts-api's repository](https://github.com/travisvn/chatterbox-tts-api). | | [CosyVoice](/tools/funaudiollm-cosyvoice.md) | [chatterbox-tts-api](/tools/travisvn-chatterbox-tts-api.md) | | --- | --- | --- | | Tagline | Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment. | Local OpenAI-compatible text-to-speech API using Chatterbox | | Stars | 22,870 | 666 | | Forks | 2,631 | 152 | | Open issues | 719 | 16 | | Language | Python | Python | | 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. | Chatterbox-TTS-API is a locally hosted Python-based text-to-speech API with capabilities similar to ElevenLabs, offering an OpenAI-compatible interface for generating voice-cloned speech. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Chatterbox-TTS-API is distributed under the AGPL-3.0 license, ensuring any modifications or derivative works must be shared openly. | | Categories | Inference & Serving, Model Training, Speech & Audio | Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [CosyVoice](/tools/funaudiollm-cosyvoice.md) | [chatterbox-tts-api](/tools/travisvn-chatterbox-tts-api.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Slowing (36%) | | Days since push | 89d | 232d | | Open issues (now) | 719 | 16 | | Stars delta | +497 (30d) | Unknown | | Open issues delta | -37 (30d) | Unknown | | Owner type | Organization | User | | Full report | [trust report](/tools/funaudiollm-cosyvoice/trust.md) | [trust report](/tools/travisvn-chatterbox-tts-api/trust.md) | ## Shared compatibility - **Python**: [CosyVoice](/tools/funaudiollm-cosyvoice.md) - Python runtime; [chatterbox-tts-api](/tools/travisvn-chatterbox-tts-api.md) - Python runtime ## 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. ## Decision facts: chatterbox-tts-api - **Requirements:** Requires a local setup environment that supports CUDA for optimal performance; Docker can simplify deployment. - **Adopt for:** Chatterbox-TTS-API is a locally hosted Python-based text-to-speech API with capabilities similar to ElevenLabs, offering an OpenAI-compatible interface for generating voice-cloned speech. - **License detail:** Chatterbox-TTS-API is distributed under the AGPL-3.0 license, ensuring any modifications or derivative works must be shared openly. ## Choose when ### Choose CosyVoice if… - License: CosyVoice is Apache-2.0, chatterbox-tts-api 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. ### Choose chatterbox-tts-api if… - License: chatterbox-tts-api is AGPL-3.0, CosyVoice is Apache-2.0. - Requirements: Requires a local setup environment that supports CUDA for optimal performance; Docker can simplify deployment.. - Tags unique to chatterbox-tts-api: ai, chatterbox, cuda, docker. - When you need a self-hosted solution that mirrors the functionality of ElevenLabs or other proprietary TTS services and requires compatibility with existing ecosystems like Open WebUI or AnythingLLM. ## 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. ## When NOT to use chatterbox-tts-api - If you require integrations specific to ElevenLabs' proprietary voice models as Chatterbox-TTS-API, despite its capabilities, does not directly support their unique voice libraries. - For users needing a fully managed service without the complexities of local deployment and maintenance, like that offered by cloud-based TTS providers. ## Common questions ### What is the difference between CosyVoice and chatterbox-tts-api? CosyVoice: Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment.. chatterbox-tts-api: Local OpenAI-compatible text-to-speech API using Chatterbox. See the comparison table for live GitHub stats and shared categories. ### When should I choose CosyVoice over chatterbox-tts-api? Choose CosyVoice over chatterbox-tts-api when License: CosyVoice is Apache-2.0, chatterbox-tts-api 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 choose chatterbox-tts-api over CosyVoice? Choose chatterbox-tts-api over CosyVoice when License: chatterbox-tts-api is AGPL-3.0, CosyVoice is Apache-2.0; Requirements: Requires a local setup environment that supports CUDA for optimal performance; Docker can simplify deployment.; Tags unique to chatterbox-tts-api: ai, chatterbox, cuda, docker; When you need a self-hosted solution that mirrors the functionality of ElevenLabs or other proprietary TTS services and requires compatibility with existing ecosystems like Open WebUI or AnythingLLM. ### 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. ### When should I avoid chatterbox-tts-api? If you require integrations specific to ElevenLabs' proprietary voice models as Chatterbox-TTS-API, despite its capabilities, does not directly support their unique voice libraries. For users needing a fully managed service without the complexities of local deployment and maintenance, like that offered by cloud-based TTS providers. ### Is CosyVoice or chatterbox-tts-api more popular on GitHub? CosyVoice has more GitHub stars (22,870 vs 666). Stars measure visibility, not whether either tool fits your constraints. ### Are CosyVoice and chatterbox-tts-api open source? Yes - both are open-source projects on GitHub (CosyVoice: Apache-2.0, chatterbox-tts-api: AGPL-3.0). ### Where can I find alternatives to CosyVoice or chatterbox-tts-api? GraphCanon lists graph-backed alternatives at [CosyVoice alternatives](/tools/funaudiollm-cosyvoice/alternatives) and [chatterbox-tts-api alternatives](/tools/travisvn-chatterbox-tts-api/alternatives) ([CosyVoice markdown twin](/tools/funaudiollm-cosyvoice/alternatives.md), [chatterbox-tts-api markdown twin](/tools/travisvn-chatterbox-tts-api/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/funaudiollm-cosyvoice-vs-travisvn-chatterbox-tts-api.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, CosyVoice or chatterbox-tts-api? CosyVoice: Steady. chatterbox-tts-api: Slowing. 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 CosyVoice and chatterbox-tts-api? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [CosyVoice trust report](/tools/funaudiollm-cosyvoice/trust); [chatterbox-tts-api trust report](/tools/travisvn-chatterbox-tts-api/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=funaudiollm-cosyvoice`](/api/graphcanon/graph?tool=funaudiollm-cosyvoice) - 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/_