# DigitalPhonetics/IMS-Toucan

Controllable and fast Text-to-Speech for over 7000 languages!

Repository: https://github.com/DigitalPhonetics/IMS-Toucan
Canonical: https://ross.abutalabs.com/products/ims-toucan
Language: Python
License: Apache-2.0
License Family: permissive
Topics: text-to-speech, toolkit, speech-synthesis, deep-learning, speech-processing, tts, pytorch, speech
Last push: 2026-01-25T14:45:14+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 64, release rhythm 40, longevity 100
- inputs: {"age_days": 1854, "days_push": 220, "days_rel": 695, "gap_med": 14, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2207, forks 316 (observed 2026-08-28T04:06:26.050852+00:00)

## What it is
IMS Toucan is a PyTorch-based toolkit for training and running state-of-the-art, controllable text-to-speech synthesis, home of the massively multilingual ToucanTTS model supporting over 7000 languages. It is developed at the University of Stuttgart and designed to be fast and trainable without massive compute.

## Use cases
- synthesize speech in many languages including low-resource ones
- train a custom TTS model on my own dataset
- generate controllable speech with prosody and speaker control
- run fast TTS inference without a GPU
- build a multilingual voice assistant or audiobook pipeline
- experiment with speech synthesis research models

## When to choose
- you need multilingual or low-resource language TTS coverage
- you want to train or fine-tune TTS models on modest hardware
- you need a Python toolkit with pretrained models and an Apache-2.0 license

## When to avoid
- you need production cloud TTS with managed APIs
- you only need simple English TTS with minimal setup
- you need real-time streaming TTS in non-Python environments

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, deep-learning, audio-processing
- domain: speech-processing, machine-learning
- platform: python, windows
- tags: text-to-speech, speech-synthesis, multilingual, pytorch, toucantts, voice-cloning, low-resource-languages, natural-language-processing, audio, linux, gpu

## Member repositories
- DigitalPhonetics/IMS-Toucan (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:26.050852+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 2026-08-30T02:46:27.614458+00:00, confidence not recorded.
  - readme: https://github.com/DigitalPhonetics/IMS-Toucan (fetched 2026-08-28T04:06:26.050852+00:00, sha db1e55023545)
- Data as of 2026-08-30T08:39:29.467469+00:00.