# r9y9/deepvoice3_pytorch

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

Repository: https://github.com/r9y9/deepvoice3_pytorch
Canonical: https://ross.abutalabs.com/products/deepvoice3_pytorch
Homepage: https://r9y9.github.io/deepvoice3_pytorch/
Language: Python
License: NOASSERTION
License Family: other
Topics: tts, speech-synthesis, end-to-end, speech-processing, machine-learning, pytorch, python, multi-speaker
Last push: 2023-12-19T04:21:47+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3228, "days_push": 988, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1975, forks 481 (observed 2026-08-28T04:06:01.313686+00:00)

## What it is
A PyTorch implementation of Deep Voice 3 and related convolutional neural network-based text-to-speech synthesis models. It includes training code, dataset preprocessors (LJSpeech, JSUT, VCTK), language-dependent text frontends for English and Japanese, and pre-trained single- and multi-speaker models.

## Use cases
- train a text-to-speech model in pytorch
- synthesize speech from text with deep voice 3
- build a multi-speaker tts model on vctk
- convert text to speech for english and japanese
- experiment with convolutional sequence-to-sequence tts models
- fine-tune a pretrained tts model on a custom dataset

## When to choose
- you want a research-grade PyTorch implementation of Deep Voice 3
- you need single- or multi-speaker TTS training on LJSpeech, JSUT, or VCTK
- you want pretrained models and audio sample references for TTS experiments

## When to avoid
- you need a production-ready, actively maintained TTS system
- you want the latest state-of-the-art neural TTS architectures
- you need a simple plug-and-play TTS API without training

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, machine-learning, deep-learning, nlp
- domain: speech-processing, machine-learning, deep-learning
- platform: python
- tags: pytorch, deep-voice-3, speech-synthesis, multi-speaker, ljspeech, vctk, convolutional-sequence-learning, audio, linux, macos, gpu

## Member repositories
- r9y9/deepvoice3_pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:01.313686+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:04:54.109978+00:00, confidence not recorded.
  - readme: https://github.com/r9y9/deepvoice3_pytorch (fetched 2026-08-28T04:06:01.313686+00:00, sha 520c88861c19)
  - homepage: https://r9y9.github.io/deepvoice3_pytorch/ (fetched 2026-08-29T10:43:59.477150+00:00, sha 9ccb2ed9b040)
- Data as of 2026-08-30T08:39:29.467469+00:00.