Open elacosse opened 6 months ago
Datamodels needed: OpenAI ElevenLab Text to Speech VLM - visual language model (OpenAI GPT-4V) Whisper Speech to Text
Basis for bot behavior OpenAI GPT-4 phenomenological problem interviewer prompt engineering (Work in Progress, Eric's job).
High-level data flow logic based on types:
If speech audio is sent, then it responds in speech audio. If text is sent, it responds in text. If image is sent, it responds in text.
Let's have this basic behavior before incorporating the OSINT features.
Click here
Datamodels needed: OpenAI ElevenLab Text to Speech VLM - visual language model (OpenAI GPT-4V) Whisper Speech to Text
Basis for bot behavior OpenAI GPT-4 phenomenological problem interviewer prompt engineering (Work in Progress, Eric's job).
High-level data flow logic based on types:
If speech audio is sent, then it responds in speech audio. If text is sent, it responds in text. If image is sent, it responds in text.