v0.0.6
Add speech-to-text transcription and translation features
This introduces the ability to transcribe and translate spoken words from audio and video files.
Users can now:
- Transcribe audio and video content into text.
- Translate spoken words in audio and video content.
- Provide a prompt for context or to specify the spelling of unfamiliar words.
- Control the variability of transcriptions and translations with a temperature parameter.
- Choose from various response formats, including JSON, verbose JSON, and plain text.
This functionality enhances the capabilities of the library, making it more versatile and useful for processing audio and video data.