# Kyubyong/dc_tts

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

Repository: https://github.com/Kyubyong/dc_tts
Canonical: https://ross.abutalabs.com/products/dc_tts
Language: Python
License: Apache-2.0
License Family: permissive
Topics: speech, speech-to-text, tts
Last push: 2023-04-14T14:54:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3206, "days_push": 1237, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1156, forks 360 (observed 2026-08-28T04:03:48.102215+00:00)

## What it is
A TensorFlow implementation of DC-TTS, a text-to-speech model based on deep convolutional networks with guided attention. It includes training pipelines for Text2Mel and SSRN components and was trained on English and Korean speech datasets.

## Use cases
- synthesize speech from text
- train a text-to-speech model on my own voice data
- reproduce the DC-TTS paper
- build a TTS model for Korean speech
- experiment with convolutional text-to-speech architectures

## When to choose
- you want to study or reproduce the DC-TTS architecture in TensorFlow
- you need a trainable TTS model for English or Korean single-speaker datasets
- you want a research-oriented TTS codebase to learn from

## When to avoid
- you need production-grade, actively maintained TTS
- you prefer PyTorch or modern TTS frameworks
- you need multi-speaker or zero-shot voice cloning

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, deep-learning, machine-learning
- domain: speech-processing, deep-learning
- platform: python
- tags: tensorflow, dc-tts, text-to-speech, speech-synthesis, guided-attention, convolutional-networks, natural-language-processing

## Member repositories
- Kyubyong/dc_tts (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:48.102215+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 2026-08-30T06:32:05.743060+00:00, confidence not recorded.
  - readme: https://github.com/Kyubyong/dc_tts (fetched 2026-08-28T04:03:48.102215+00:00, sha e4ba52bc0924)
- Data as of 2026-08-30T08:39:29.467469+00:00.