Openai Whisper Api
Transcribe local audio files using OpenAI’s Whisper transcription endpoint from the command line. Supports selecting the model, setting language and prompts, and outputting either plain text or JSON to a specified file.
SafeAI/MLsteipetev1.0.0
Use Cases
- Generate text transcripts from meeting recordings (m4a/ogg) for notes and search
- Create JSON transcripts for downstream NLP pipelines or indexing
- Force transcription language for multilingual audio to improve accuracy
- Provide a prompt with speaker names or context to guide transcription formatting
openaiwhisperspeech-to-texttranscriptionaudiocurlcliapijsondeveloper-tools