Following up on the previous demo โ I will now added text-to-speech support using gpt-4o-mini-tts ๐
The chatbot already responded with text and generated images, and now it will also speaks the response โ making the experience more dynamic and engaging.
๐ง You ask a question via text,
๐จ๏ธ It replies in text,
๐ผ๏ธ Generates a relevant image,
๐ฃ๏ธ And now also speaks the reply using TTS.
This is part of my ongoing exploration of multimodal AI.
Ali Mehdi
Following up on the previous demo โ I will now added text-to-speech support using gpt-4o-mini-tts ๐
The chatbot already responded with text and generated images, and now it will also speaks the response โ making the experience more dynamic and engaging.
๐ง You ask a question via text,
๐จ๏ธ It replies in text,
๐ผ๏ธ Generates a relevant image,
๐ฃ๏ธ And now also speaks the reply using TTS.
This is part of my ongoing exploration of multimodal AI.
Canโt wait to share the next iteration!
#AI #Chatbot #GPT4o #TTS #Multimodal #VoiceAI #GenerativeAI #OpenAI #Innovation #Tech #BuildInPublic
9 months ago | [YT] | 1
View 0 replies