--- title: "WaveRNN vs dc_tts" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/fatchord-wavernn-vs-kyubyong-dc-tts" tools: ["fatchord-wavernn", "kyubyong-dc-tts"] --- # WaveRNN vs dc_tts *GraphCanon updated Jul 30, 2026* ## Verdict Pick WaveRNN if waveRNN is a Python-based neural vocoder that can generate high-quality speech from text when used with TTS models like Tacotron; pick dc_tts if dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. [WaveRNN](https://fatchord.github.io/model_outputs/) reports 2.2k GitHub stars, 687 forks, and 108 open issues, last pushed Jul 2, 2022. [dc_tts](https://github.com/Kyubyong/dc_tts) has 1.2k stars, 360 forks, and 68 open issues, last pushed Apr 14, 2023. Figures are from public GitHub metadata via [WaveRNN's repository](https://github.com/fatchord/WaveRNN) and [dc_tts's repository](https://github.com/Kyubyong/dc_tts). | | [WaveRNN](/tools/fatchord-wavernn.md) | [dc_tts](/tools/kyubyong-dc-tts.md) | | --- | --- | --- | | Tagline | WaveRNN Vocoder + TTS | A TensorFlow Implementation of DC-TTS | | Stars | 2,190 | 1,156 | | Forks | 687 | 360 | | Open issues | 108 | 68 | | Language | Python | Python | | Adopt for | WaveRNN is a Python-based neural vocoder that can generate high-quality speech from text when used with TTS models like Tacotron. | dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | Speech & Audio | Speech & Audio | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [WaveRNN](/tools/fatchord-wavernn.md) | [dc_tts](/tools/kyubyong-dc-tts.md) | | --- | --- | --- | | Days since push | 1488d | 1203d | | Open issues (now) | 108 | 68 | | Full report | [trust report](/tools/fatchord-wavernn/trust.md) | [trust report](/tools/kyubyong-dc-tts/trust.md) | ## Decision facts: WaveRNN - **Requirements:** Python version must be equal to or higher than 3.6; Pytorch 1 with CUDA support is a prerequisite - **Adopt for:** WaveRNN is a Python-based neural vocoder that can generate high-quality speech from text when used with TTS models like Tacotron. ## 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. ## Choose when ### Choose WaveRNN if… - License: WaveRNN is MIT, dc_tts is Apache-2.0. - Requirements: Python version must be equal to or higher than 3.6; Pytorch 1 with CUDA support is a prerequisite. - Tags unique to WaveRNN: neural-vocoder, pytorch, speech-synthesis, tacotron. - When you require a compact and efficient method to produce natural-sounding speech synthesis, specifically with the need for high fidelity in audio quality. ### Choose dc_tts if… - License: dc_tts is Apache-2.0, WaveRNN 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. - dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. ## When NOT to use WaveRNN - Avoid using when you need extensive customization of the vocoder parameters, since it is optimized for specific configurations and might not offer the level of tweakability other frameworks provide. - Not recommended if your setup does not support CUDA, as WaveRNN requires PyTorch with CUDA for execution. ## 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. ## Common questions ### What is the difference between WaveRNN and dc_tts? WaveRNN: WaveRNN Vocoder + TTS. dc_tts: A TensorFlow Implementation of DC-TTS. See the comparison table for live GitHub stats and shared categories. ### When should I choose WaveRNN over dc_tts? Choose WaveRNN over dc_tts when License: WaveRNN is MIT, dc_tts is Apache-2.0; Requirements: Python version must be equal to or higher than 3.6; Pytorch 1 with CUDA support is a prerequisite; Tags unique to WaveRNN: neural-vocoder, pytorch, speech-synthesis, tacotron; When you require a compact and efficient method to produce natural-sounding speech synthesis, specifically with the need for high fidelity in audio quality. ### When should I choose dc_tts over WaveRNN? Choose dc_tts over WaveRNN when License: dc_tts is Apache-2.0, WaveRNN 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; dc_tts is a text-to-speech model based on TensorFlow and requires specific version dependencies. ### When should I avoid WaveRNN? Avoid using when you need extensive customization of the vocoder parameters, since it is optimized for specific configurations and might not offer the level of tweakability other frameworks provide. Not recommended if your setup does not support CUDA, as WaveRNN requires PyTorch with CUDA for execution. ### 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. ### Is WaveRNN or dc_tts more popular on GitHub? WaveRNN has more GitHub stars (2,190 vs 1,156). Stars measure visibility, not whether either tool fits your constraints. ### Are WaveRNN and dc_tts open source? Yes - both are open-source projects on GitHub (WaveRNN: MIT, dc_tts: Apache-2.0). ### Where can I find alternatives to WaveRNN or dc_tts? GraphCanon lists graph-backed alternatives at [WaveRNN alternatives](/tools/fatchord-wavernn/alternatives) and [dc_tts alternatives](/tools/kyubyong-dc-tts/alternatives) ([WaveRNN markdown twin](/tools/fatchord-wavernn/alternatives.md), [dc_tts markdown twin](/tools/kyubyong-dc-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/fatchord-wavernn-vs-kyubyong-dc-tts.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, WaveRNN or dc_tts? WaveRNN: Dormant. dc_tts: Dormant. 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 WaveRNN and dc_tts? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [WaveRNN trust report](/tools/fatchord-wavernn/trust); [dc_tts trust report](/tools/kyubyong-dc-tts/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=fatchord-wavernn`](/api/graphcanon/graph?tool=fatchord-wavernn) - 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/_