I am working on creating an AI based voice assistant and the python code for voice assistance works perfectly i used udp to convert the audio response generated by ChatGPT into small packets and was able to recieve it on the omniverseA2F but after that i want that audio file to be played at Audio player Streaming directly on Real-Time is there a solution or a reference project that could help me with this i am new to omniverse and i am having a hard time understanding it i also need details on Riva TTS if that could be an optimal solution to send text based responses and then convert it to voice and face in real time
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Audio2Face Export support for reatime audio and javis generated audio | 4 | 799 | May 10, 2021 | |
| Audio2Face 2021.2 Open Beta Released | 1 | 672 | April 21, 2021 | |
| Audio2Face SAAS | 29 | 5691 | November 27, 2023 | |
| Python API/SDK to inject custom parameters. in omniverse audio2face | 12 | 3417 | April 29, 2022 | |
| Build a simple avatar with ASR, Sentence-transformer, Semantic Similarity Search, TTS and Omniverse Audio2Face | 4 | 5083 | May 27, 2022 | |
| Using audio2face for realtime audio to video conversation? | 2 | 1062 | March 29, 2023 | |
| Can Audio2face do live stream to metahuman? | 28 | 6006 | August 16, 2023 | |
| Audio2Face stand alone application deployment | 4 | 1289 | May 31, 2023 | |
| Unreal Engine Speech audio to Audio2Face? | 1 | 755 | July 7, 2023 | |
| Use audio2face for avatar chatbot | 10 | 3155 | July 24, 2023 |