Upload README.md with huggingface_hub

README.md

@@ -19,7 +19,7 @@ tags:
 datasets:
   - gryphe/styletune-roleplay-200
 ---
-> **New in v3.0** — `--speak` (voice speaks through `output.weight`, invented if absent when head/embed geometry survives; GGUF targets only), smarter multi-tensor mapping (same-role bridging across prefixes, one batched error instead of mid-cast surprises), and a one-line install via the tarball below. 12 commands, `voice --help` is truth.
+> **New in v3.1** — `voice graft` (DELLA single graft, pulse→donor) and `voice chorus` (blend pulse + support + lead, `--config` stages knob screens per graft with an auditionable duet). 14 commands, `voice --help` is truth.
 
 <p align="center"><img src="./lockup-circle-wordmark-2-refined.png" width="360" alt="Voice" /></p>
 
@@ -171,7 +171,7 @@ The notebook is still mostly empty. That's why the next line matters most.
 
 ## Commands
 
-Three you need daily — rest in [`DOCS.md`](./DOCS.md) (`voice --help` is truth, 12 commands `v3.0.1`):
+Three you need daily — rest in [`DOCS.md`](./DOCS.md) (`voice --help` is truth, 14 commands `v3.1`):
 
 | Command | What it does |
 |---|---|
@@ -184,7 +184,8 @@ Three you need daily — rest in [`DOCS.md`](./DOCS.md) (`voice --help` is truth
 |---|---|
 | `voice add <safetensors> <json>` | Add local `voice.safetensors` + `voice.json` to `~/.voices/` (both required, asks name) |
 | `voice get <repo> [tensors...]` | Extract head (default) or named tensors (`--multi` → `voicepack.safetensors` + json, BF16 preserved) |
-| `voice delta [name]` | Make a portable `voice − base` style |
+| `voice graft <pulse> [donor]` | Graft one voice onto another (DELLA single graft, `--density/--epsilon/--lambda/--rescale/--seed/--out`) |
+| `voice chorus [pulse] [donors...]` | Blend pulse + support + lead (0.8 first graft, 0.9 lead; support Enter-to-skip → duet; `--config` stages knobs with auditionable duet) |
 | `voice list [base]` | List voices or cached bases |
 | `voice info <voice>` | Show voice details |
 | `voice remove <voice>` | Remove a voice |
@@ -211,7 +212,7 @@ voice list base
 voice cast ./model.gguf styletune-v2 --out ./voiced/
 ```
 
-> `delta-` is reserved. Voice names cannot start with it. Deltas always do. Full CLI reference: [`DOCS.md`](./DOCS.md) (generated from `voice --help`, 12 commands). Names are lowercased when saved.
+> `delta-` is reserved. Voice names cannot start with it. Deltas always do. Full CLI reference: [`DOCS.md`](./DOCS.md) (generated from `voice --help`, 14 commands). Names are lowercased when saved.
 
 ## What StyleTune showed