C# .NET Core API for Audio Transcription
Budget: $30 – $250 USD
I need a C# .NET Core API that can receive a WAV file and return a JSON with the transcription. The transcription should separate each speaker and detail the time span of each sentence or utterance. The solution must utilize Azure Speech or Azure Open AI.
Key Requirements:
- The API should handle audio files up to 30 minutes in length.
- It should be capable of recognizing and separating multiple speakers (more than two).
- The transcription should be of high accuracy.
Ideal Skills and Experience:
- Proficiency in C# and .NET Core.
- Extensive experience with creating APIs.
- Familiarity with Azure Speech and Azure Open AI.
- Previous work with audio file processing and transcription.
- Strong understanding of JSON formatting.
Key Requirements:
- The API should handle audio files up to 30 minutes in length.
- It should be capable of recognizing and separating multiple speakers (more than two).
- The transcription should be of high accuracy.
Ideal Skills and Experience:
- Proficiency in C# and .NET Core.
- Extensive experience with creating APIs.
- Familiarity with Azure Speech and Azure Open AI.
- Previous work with audio file processing and transcription.
- Strong understanding of JSON formatting.