add roxi-duplex to org card

README.md

@@ -6,16 +6,7 @@ pinned: false
 
 # IOTEverythin
 
-We build small, production-oriented AI that runs where the data lives. Two
-independent product lines: compact Indian-English text-to-speech for
-conversational agents, and grounded question answering that quotes your
-documents instead of hallucinating.
-
----
-
-# Voice / Text-to-Speech
-
-Compact, production-oriented text-to-speech voices for conversational AI, with a
+We build compact, production-oriented text-to-speech voices for conversational AI, with a
 focus on Indian-English for customer-support and website voice assistants.
 
 ## VozVox
@@ -23,11 +14,17 @@ focus on Indian-English for customer-support and website voice assistants.
 These voices power [VozVox](https://www.vozvox.com/), our voice agent platform for
 AI-powered conversational agents across phone and web, with natural-sounding speech.
 
+## Roxi-Duplex: full-duplex speech-to-speech
+
+[roxi-duplex](https://huggingface.co/IOTEverythin/roxi-duplex) is a LoRA adapter for Kyutai's
+Moshi that turns it into a full-duplex Indian-English customer-support voice agent. It listens
+and speaks simultaneously, so interruptions and backchannels work naturally.
+
 ## The Roxi TTS line
 
-A family of Indian-English voices fine-tuned from the open MOSS-TTS models. Two
-tiers: the 0.1B models run in real time for live agents, and the 1.7B model is for
-pre-rendered or premium-quality audio.
+A family of Indian-English voices fine-tuned from the open MOSS-TTS models. Two tiers: the
+0.1B models run in real time for live agents, and the 1.7B model is for pre-rendered or
+premium-quality audio.
 
 | Model | Base | Best for |
 |---|---|---|
@@ -38,28 +35,13 @@ pre-rendered or premium-quality audio.
 | roxi-tts-v2-onnx | ONNX build of v2 | CPU inference, no transformers dependency |
 | voxi-tts | MOSS-TTS-Nano 0.1B | Original prototype voice |
 
-**Focus:** Indian-English accent, natural and telephony-aware; small and fast;
-built on commercially permissive Apache-2.0 base models; single-speaker branded
-voices for support calls and website assistants.
-
-**Attribution:** Models are built on MOSS-TTS (Apache-2.0). Training data includes
-the IIT-Madras Indic TTS English set, used with the required copyright notice shown
-on each model card.
-
----
-
-# Grounded QA
+## Focus
 
-[grounded-pointer-qa](https://huggingface.co/IOTEverythin/grounded-pointer-qa) is an
-extractive question-answering model that **cannot hallucinate by construction**: it
-only quotes verbatim spans from your documents, abstains when the answer is not
-there, and decodes deterministically. Knowledge is hot-swappable: point it at a
-folder of `.txt`/`.md`/`.pdf` files, with no retraining.
+- Indian-English accent, natural and telephony-aware
+- Small and fast, built on commercially permissive Apache-2.0 base models
+- Single-speaker branded voices for support calls and website assistants
 
-Built on roberta-base (125M), it runs in milliseconds on consumer hardware: 74.6 EM
-on SQuAD v2 in a full-retrieval setting, and 91.7% answer precision in its "right or
-silent" mode. A natural grounding layer for support agents that must quote policy
-documents instead of improvising.
+## Attribution
 
-**Focus:** grounded, verifiable answers; every answer a verbatim quote with a
-source, or an honest abstention; local-first and deterministic.
+Models are built on MOSS-TTS (Apache-2.0). Training data includes the IIT-Madras Indic TTS
+English set, used with the required copyright notice shown on each model card.