AI Endpoints : catalogue et playground

Comparez et testez des modèles open weight pour le texte, le code, la voix et la vision, sans inscription. Passez ensuite en production avec la même API compatible OpenAI.

Nouveau

solaria-3

Speech To Text

Solaria-3 is Gladia's latest speech-to-text model, delivering its highest accuracy on real-world European audio. It transcribes English, French, German, Spanish and Italian (one language per transcription, no code switching) and gives access to Gladia's Audio Intelligence add-ons such as speaker diarization, translation, named entity recognition and sentiment analysis.

Tarification
0,00204 MAD/ seconde d'audio
Ajouté au catalogue le
19 nov. 2026
Licence
Proprietary (Gladia)
Formats de sortie
json
Formats audio pris en charge
aac, ac3, eac3, flac, m4a, mp2, mp3, ogg, opus, wav, 3g2, 3gp, avi, flv, m4v, matroska, mov, mp4, wmv
Durée audio max
3h
Taille audio max
2048 MB
https://oai.endpoints.kepler.ai.cloud.ovh.net/gladia