# keithito/tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

Repository: https://github.com/keithito/tacotron
Canonical: https://ross.abutalabs.com/products/tacotron
Language: Python
License: MIT
License Family: permissive
Topics: tacotron, tensorflow, speech-synthesis, python, machine-learning, tts
Last push: 2023-07-06T21:12:04+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3343, "days_push": 1154, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2995, forks 937 (observed 2026-08-28T04:07:36.959811+00:00)

## What it is
An unofficial open-source TensorFlow implementation of Google's Tacotron end-to-end neural text-to-speech model, with a pre-trained model available. It supports both inference via a demo web server and training on speech datasets like LJ Speech.

## Use cases
- synthesize speech from text with a neural tts model
- train a tacotron text-to-speech model on my own dataset
- run a pretrained tacotron model locally
- experiment with end-to-end speech synthesis in tensorflow
- generate audio from text using lj speech trained model

## When to choose
- you want an open-source Tacotron implementation to study or extend
- you need a pre-trained model for quick text-to-speech inference
- you want to train a TTS model on LJ Speech or a compatible dataset

## When to avoid
- you need state-of-the-art TTS quality or modern architectures like Tacotron 2 or VITS
- you use TensorFlow 2.x or PyTorch exclusively
- you need actively maintained code with recent dependency support

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, machine-learning, deep-learning
- domain: speech-processing, machine-learning, deep-learning
- platform: python
- tags: tacotron, tensorflow, speech-synthesis, text-to-speech, neural-tts, pretrained-model, linux, gpu

## Member repositories
- keithito/tacotron (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:36.959811+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 2026-08-30T07:30:47.524518+00:00, confidence not recorded.
  - readme: https://github.com/keithito/tacotron (fetched 2026-08-28T04:07:36.959811+00:00, sha c45fb58af47f)
- Data as of 2026-08-30T08:39:29.467469+00:00.