Course overview
Explores multimodal features of the OpenAI API: speech processing, transcription and translation. The course demonstrates creating podcast and call transcriptions, handling non‑English languages, and translating transcriptions into English or Portuguese.
Covers multimodal use cases of the OpenAI API focused on speech‑to‑text and translation.
Provides concrete workflows: transcribing a podcast, processing customer calls and detecting speaker language.
Describes how to translate transcriptions (e.g. Portuguese → English) for integration into customer‑support workflows.
2lessons
2lessons
9activities
2exercises
7videos
Skills and topics covered
Access the platform
Open the catalogue to review course details, access conditions, and your personal progress. Sign in.