6 Services from openai.mpp.tempo.xyz

Converts input text into spoken audio using OpenAI's TTS models and voices, returning an audio file in the specified format

Generate original images from text prompts using OpenAI's DALL-E model

Transcribes audio files into text using OpenAI's Whisper speech recognition model

Sends a multi-turn conversation to OpenAI GPT-4o, GPT-4, o1, and other models and returns a text completion response

Converts text into high-dimensional vector embeddings for semantic search, clustering, and similarity tasks

Stateful multi-turn AI responses using OpenAI models (Codex, GPT-4o, etc.) with built-in tool use and conversation management