In August of 2022, we managed to accomplish nothing short of a research breakthrough. InfinityContext feeds prompts without length limitation to a modified version of our first language model.
Speech-to-text APIs have made it possible to transcribe podcasts automatically. New speaker categorization feature can identify up to 100 speakers in one audio file. Transcription can help content creators reach a broader audience and promote inclusivity.
"Magic speech-to-text is a new API based on our in-house large ASR model. It's incredibly easy to integrate into your application and can handle as many use cases as possible. Integration is incredibly simple - just a few lines of code and you're ready to go.
The Magic-Summary text summarisation API can be used for a lot of things. Here are 5 real life examples of how you can use our API in a new way. Our goal is to make the use of AI possible and affordable for every developer.