✓ Use it for content generation purposes
✓ Map-out Q&A pairs with your product, service or brand
✓ Research any topic and get Q&A pairs from that seed topic
✓ Differentiate your pages!
✓ Optimise code to increase speed ⚡
✓ Increase RAM capacity to mitigate bumps and allow for more content to be analysed
✓ Provide additional Q&A algorithms
Kudos to @huggingFaces and @Streamit DevOps for their support so far! 🙌
8/10
📂 About open-sourcing the code:
That code currently lies in a private repo. I should be able to make it public soon for you to re-use it in your own apps and creations!
Keep your eyes peeled! 🙌
9/10
WTFaq is still in beta, head-off to my Gitter page for bug reports, Qs or suggestions:
▶️ gitter.im/DataChaz/what-…
This app is free! You can buy me a ☕ to support my work if it's useful to you!
▶️ buymeacoffee.com/cwar05
NVIDIA just removed one of the biggest friction points in Voice AI.
PersonaPlex-7B is an open-source, full-duplex conversational model.
Free, open source (MIT), with open model weights on @huggingface 🤗
Links to repo and weights in 🧵↓
The traditional ASR → LLM → TTS pipeline forces rigid turn-taking.
It’s efficient, but it never feels natural.
PersonaPlex-7B changes that.
This @nvidia model can listen and speak at the same time.
It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components.
That unlocks:
→ instant back-channel responses
→ interruptions that feel human
→ real conversational rhythm
Persona control is fully zero-shot!
If you’re building low-latency assistants or support agents, this is a big step forward 🔥