OpenAI API: Speech
29mIntermediate2024-01-31
Authors
Ronnie Sheer
Software Developer and Instructor
Course details
The game-changing text-to-speech and speech-to-text APIs in OpenAI may set a new standard for voice activated software. Developers can increasingly benefit from proficiency with these APIs. Since its release, Whisper Model has completely disrupted the STT/TTS space. In this hands-on course, software developer and instructor Ronnie Sheer shows you how to leverage the voice APIs in OpenAI. Learn about voice models and the AI revolution. Get useful overviews of STT/TTS, then dive into actually building a small text reading web app and a pronunciation coach. After completing this course, you will be able to incorporate STT/TTS capabilities into your software in genuinely meaningful and useful ways.
Skills covered
OpenAI APIAPIsOpenAIGenerative AIArtificial Intelligence (AI)Software DevelopmentOne-Off
Concepts
Introduction
- Voice models and the AI revolution
- What you should know
- Using the exercise files
- Responsible usage of AI
Text-to-Speech
- Text-to-speech overview
- Setting up OpenAI library
- Test ride with the text-to-speech API
- What we will build
- Project structure
- Creating a TTS endpoint
- Challenge - Voice selection
- Solution - Voice selection
Speech-to-Text
- Speech-to-text overview
- Testing the speech-to-text API
- What we will build
- Project structure
- Using the API in an app
Conclusion
- Next steps