AI Youtuber Custom Voice Integration - 19/02/2025 02:49 EST
Budget: $150 – $300 USD
I'm using aituber-kit, which is an OpenSource, real-time conversational AI Youtuber concept.
This Open Source has an LLM that generates responses and a TTS that generates speech that can be called via API,
You can type in text or microphone and an AI character will answer you.
I chose the GPT-4o-Audio-Preview model of the LLM provided by default,
This Audio model can only use the basic voices provided by Openai, so I want to modify it.
After selecting the GPT-4o-Audio model, when the user enters Text or Voice, the Audio LLM will generate the appropriate response in Text,
To output this as the desired voice, we need to enter the Text response into the TTS in Local and use the
I want the Text response to be output as Speech in the Local TTS.
It's open source, written in Node js, Typescript, React, and more, and uses the
Overall, it requires an understanding of AI or AI TTS systems and
I hope you can understand what I am asking for. (Combining Local TTS with GPT 4o Audio model in Open Source)
This Open Source has an LLM that generates responses and a TTS that generates speech that can be called via API,
You can type in text or microphone and an AI character will answer you.
I chose the GPT-4o-Audio-Preview model of the LLM provided by default,
This Audio model can only use the basic voices provided by Openai, so I want to modify it.
After selecting the GPT-4o-Audio model, when the user enters Text or Voice, the Audio LLM will generate the appropriate response in Text,
To output this as the desired voice, we need to enter the Text response into the TTS in Local and use the
I want the Text response to be output as Speech in the Local TTS.
It's open source, written in Node js, Typescript, React, and more, and uses the
Overall, it requires an understanding of AI or AI TTS systems and
I hope you can understand what I am asking for. (Combining Local TTS with GPT 4o Audio model in Open Source)