--- title: "dc_tts vs Matcha-TTS" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kyubyong-dc-tts-vs-shivammehta25-matcha-tts" tools: ["kyubyong-dc-tts", "shivammehta25-matcha-tts"] --- # dc_tts vs Matcha-TTS *GraphCanon updated Jul 30, 2026* ## Verdict Pick dc_tts if dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies; pick Matcha-TTS if matcha-TTS employs non-autoregressive probabilistic techniques with deep learning for fast TTS generation. [dc_tts](https://github.com/Kyubyong/dc_tts) reports 1.2k GitHub stars, 360 forks, and 68 open issues, last pushed Apr 14, 2023. [Matcha-TTS](https://shivammehta25.github.io/Matcha-TTS/) has 1.3k stars, 213 forks, and 35 open issues, last pushed Jul 13, 2026. Figures are from public GitHub metadata via [dc_tts's repository](https://github.com/Kyubyong/dc_tts) and [Matcha-TTS's repository](https://github.com/shivammehta25/Matcha-TTS). | | [dc_tts](/tools/kyubyong-dc-tts.md) | [Matcha-TTS](/tools/shivammehta25-matcha-tts.md) | | --- | --- | --- | | Tagline | A TensorFlow Implementation of DC-TTS | Matcha-TTS is a fast TTS architecture with conditional flow matching | | Stars | 1,156 | 1,339 | | Forks | 360 | 213 | | Open issues | 68 | 35 | | Language | Python | Jupyter Notebook | | Adopt for | dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. | Matcha-TTS employs non-autoregressive probabilistic techniques with deep learning for fast TTS generation. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | Speech & Audio | Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [dc_tts](/tools/kyubyong-dc-tts.md) | [Matcha-TTS](/tools/shivammehta25-matcha-tts.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Active (82%) | | Days since push | 1203d | 16d | | Open issues (now) | 68 | 35 | | Full report | [trust report](/tools/kyubyong-dc-tts/trust.md) | [trust report](/tools/shivammehta25-matcha-tts/trust.md) | ## Decision facts: dc_tts - **Requirements:** Depends on TensorFlow >=1.3 and has compatibility issues with updated APIs for `tf.contrib.layers.layer_norm`.; Requires Python packages like NumPy, librosa, tqdm, matplotlib, and scipy. - **Adopt for:** dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. ## Decision facts: Matcha-TTS - **Adopt for:** Matcha-TTS employs non-autoregressive probabilistic techniques with deep learning for fast TTS generation. ## Choose when ### Choose dc_tts if… - dc_tts is primarily Python; Matcha-TTS is Jupyter Notebook. - License: dc_tts is Apache-2.0, Matcha-TTS is MIT. - Requirements: Depends on TensorFlow >=1.3 and has compatibility issues with updated APIs for `tf.contrib.layers.layer_norm`.; Requires Python packages like NumPy, librosa, tqdm, matplotlib, and scipy.. - Tags unique to dc_tts: speech, speech-to-text, tensorflow, tts. - dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. ### Choose Matcha-TTS if… - Matcha-TTS is primarily Jupyter Notebook; dc_tts is Python. - License: Matcha-TTS is MIT, dc_tts is Apache-2.0. - Tags unique to Matcha-TTS: deep-learning, diffusion-models, flow-matching, non-autoregressive. - When you require rapid deployment of text-to-speech engines without autoregressive dependencies ## When NOT to use dc_tts - Last GitHub push was 1229 days ago (dormant maintenance, Apr 14, 2023). Validate activity before betting a new project on dc_tts. ## When NOT to use Matcha-TTS - If your project requires real-time adaptability to user input that necessitates autoregressive methods - In scenarios where licensing flexibility is not a priority, favoring proprietary systems with dedicated support ## Common questions ### What is the difference between dc_tts and Matcha-TTS? dc_tts: A TensorFlow Implementation of DC-TTS. Matcha-TTS: Matcha-TTS is a fast TTS architecture with conditional flow matching. See the comparison table for live GitHub stats and shared categories. ### When should I choose dc_tts over Matcha-TTS? Choose dc_tts over Matcha-TTS when dc_tts is primarily Python; Matcha-TTS is Jupyter Notebook; License: dc_tts is Apache-2.0, Matcha-TTS is MIT; Requirements: Depends on TensorFlow >=1.3 and has compatibility issues with updated APIs for `tf.contrib.layers.layer_norm`.; Requires Python packages like NumPy, librosa, tqdm, matplotlib, and scipy.; Tags unique to dc_tts: speech, speech-to-text, tensorflow, tts; dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. ### When should I choose Matcha-TTS over dc_tts? Choose Matcha-TTS over dc_tts when Matcha-TTS is primarily Jupyter Notebook; dc_tts is Python; License: Matcha-TTS is MIT, dc_tts is Apache-2.0; Tags unique to Matcha-TTS: deep-learning, diffusion-models, flow-matching, non-autoregressive; When you require rapid deployment of text-to-speech engines without autoregressive dependencies. ### When should I avoid dc_tts? Last GitHub push was 1229 days ago (dormant maintenance, Apr 14, 2023). Validate activity before betting a new project on dc_tts. ### When should I avoid Matcha-TTS? If your project requires real-time adaptability to user input that necessitates autoregressive methods In scenarios where licensing flexibility is not a priority, favoring proprietary systems with dedicated support ### Is dc_tts or Matcha-TTS more popular on GitHub? Matcha-TTS has more GitHub stars (1,339 vs 1,156). Stars measure visibility, not whether either tool fits your constraints. ### Are dc_tts and Matcha-TTS open source? Yes - both are open-source projects on GitHub (dc_tts: Apache-2.0, Matcha-TTS: MIT). ### Where can I find alternatives to dc_tts or Matcha-TTS? GraphCanon lists graph-backed alternatives at [dc_tts alternatives](/tools/kyubyong-dc-tts/alternatives) and [Matcha-TTS alternatives](/tools/shivammehta25-matcha-tts/alternatives) ([dc_tts markdown twin](/tools/kyubyong-dc-tts/alternatives.md), [Matcha-TTS markdown twin](/tools/shivammehta25-matcha-tts/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/kyubyong-dc-tts-vs-shivammehta25-matcha-tts.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, dc_tts or Matcha-TTS? dc_tts: Dormant. Matcha-TTS: Active. 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 dc_tts and Matcha-TTS? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [dc_tts trust report](/tools/kyubyong-dc-tts/trust); [Matcha-TTS trust report](/tools/shivammehta25-matcha-tts/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=kyubyong-dc-tts`](/api/graphcanon/graph?tool=kyubyong-dc-tts) - 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/_