Separate Voice/TTS and Grounded QA into distinct sections

README.md

@@ -6,7 +6,18 @@ pinned: false
 
 # IOTEverythin
 
-We build compact, production-oriented text-to-speech voices for conversational AI, with a
+We build small, production-oriented AI that runs where the data lives. Two
+independent product lines:
+
+- **Voice** — compact Indian-English text-to-speech for conversational agents.
+- **Grounded QA** — extractive 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
 focus on Indian-English for customer-support and website voice assistants.
 
 ## VozVox
@@ -29,25 +40,28 @@ 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 |
 
-## Grounded QA
+**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
 
 [grounded-pointer-qa](https://huggingface.co/IOTEverythin/grounded-pointer-qa) is an
-extractive question-answering model that cannot hallucinate by construction: it only
+extractive question-answering model that **cannot hallucinate by construction**: it only
 quotes verbatim spans from your documents, abstains when the answer isn't there, and
 decodes deterministically. Knowledge is hot-swappable — point it at a folder of
-`.txt`/`.md`/`.pdf` files, no retraining. 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.
-
-## Focus
-
-- Indian-English accent, natural and telephony-aware
-- Small and fast, built on commercially permissive Apache-2.0 base models
-- Grounded, verifiable answers for agents that quote documents rather than improvise
-- Single-speaker branded voices for support calls and website assistants
+`.txt`/`.md`/`.pdf` files, no retraining.
 
-## Attribution
+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.
 
-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.
+**Focus:** grounded, verifiable answers; every answer a verbatim quote with a source, or
+an honest abstention; local-first and deterministic.