Instructions to use goaicorp/mos-tts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use goaicorp/mos-tts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="goaicorp/mos-tts")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("goaicorp/mos-tts") model = AutoModelForTextToWaveform.from_pretrained("goaicorp/mos-tts", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Request access to mos-tts
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
mos-tts is a GO AI Corp model shared for non-commercial research (CC BY-NC 4.0). Commercial use needs written permission from contact@goaicorporation.org. Please read the card, its terms and licenses before requesting access, and make sure you understand them.
Log in or Sign Up to review the conditions and access this model content.
mos-tts
GO AI Corp's product endpoint for Mooré text-to-speech. The repo name stays fixed; the model behind it can change.
| Serves | goaicorp/mos-mms-tts: same weights, checked by file hash in November 2026 |
| Published | May 2026 |
Training data, scores and limits are those of mos-mms-tts. This endpoint will be pointed to the best model once all models are re-scored on clean test sets; each change will be listed under Versions.
Résumé en français. Point d'accès « produit » de GO AI Corp pour la synthèse vocale en mooré : le nom du dépôt reste fixe, le modèle servi peut changer. Il sert aujourd'hui
mos-mms-tts(mêmes poids, vérifiés par empreinte des fichiers en novembre 2026) ; données, scores et limites sont ceux de ce modèle. Il sera dirigé vers le meilleur modèle quand tous les modèles auront été réévalués sur des jeux de test propres ; chaque changement sera noté sous Versions. Publié en mai 2026. Licence CC BY-NC 4.0 ; tout usage commercial demande l'autorisation écrite de contact@goaicorporation.org. Accès sur demande.
Quick start
import torch, scipy.io.wavfile
from transformers import VitsModel, AutoTokenizer
name = "goaicorp/mos-tts"
model, tok = VitsModel.from_pretrained(name), AutoTokenizer.from_pretrained(name)
with torch.no_grad():
wav = model(**tok("Ne y yibeoogo.", return_tensors="pt")).waveform[0].numpy()
scipy.io.wavfile.write("out.wav", model.config.sampling_rate, wav)
Versions
- May 2026: created with the weights of mos-mms-tts.
License
CC BY-NC 4.0. Commercial use needs written permission from contact@goaicorporation.org.
Developed and maintained by
- Wendyellé A. Alban NYANTUDRE: nyantudre@gmail.com
- Aristide BANDAOGO: aristide@goaicorporation.org
- Downloads last month
- 15