Publish VoxEdge public model index

README.md

@@ -0,0 +1,45 @@
+---
+license: apache-2.0
+tags:
+- onnx
+- onnxruntime
+- speech
+- text-to-speech
+- voice-conversion
+- edge-ai
+---
+
+# VoxEdge model index
+
+This is the canonical public package index for **VoxEdge**, an offering from
+**Resontra AI**. VoxEdge evaluates and packages speech and agent models for
+bounded, low-latency execution on consumer CPUs and GPUs.
+
+The machine-readable candidate inventory is `voxedge-candidates.json`. A row is
+not a performance or availability claim: only an entry with a 40-character Hub
+revision has a published immutable package. Planned and blocked entries expose
+the roadmap without publishing unreviewed weights.
+
+## Current publication set
+
+| Candidate | Task | State | Intended artifact repository |
+|---|---|---|---|
+| Qwen3 0.6B INT4 ORT | Local agent LLM | Ready for verified upload | `ResontraAI/voxedge-qwen3-06b-int4-ort` |
+| Pocket TTS English INT8 ONNX | Compact streaming TTS | Pinned; benchmark work pending | `ResontraAI/voxedge-pocket-tts-english-int8-ort` |
+| VoXtream2 | CUDA streaming TTS comparison | CUDA benchmark pending | `ResontraAI/voxedge-voxtream2-cuda` |
+| StreamVoiceAnon INT8 ORT | Voice conversion/anonymization | Local graphs verified; release gates open | `ResontraAI/voxedge-streamvoiceanon-int8-ort` |
+| RVC v2 | Voice conversion | Authorized checkpoint and components missing | `ResontraAI/voxedge-rvc-v2-ort` |
+| Beatrice v2 | Voice conversion | Provider runtime/terms pending | `ResontraAI/voxedge-beatrice-v2-runtime` |
+
+## Safety and provenance boundary
+
+Public VoxEdge repositories never contain prompt recordings, target identities,
+speaker embeddings, FAISS speaker indexes, consent records, runtime caches,
+generated review audio, secrets, or checkpoints without explicit redistribution
+rights. Speaker-specific packages are private or gated and separately deletable.
+
+Benchmark claims remain tied to their measured hardware and immutable artifact
+hashes. Cloud results do not substitute for physical consumer-device evidence.
+
+Source, schemas, and reproducibility tooling live in the
+[VoxEdgeLab repository](https://github.com/warisqr007/VoxEdgeLab).

voxedge-candidates.json

@@ -0,0 +1,69 @@
+{
+  "schema_version": "1.0",
+  "namespace": "ResontraAI",
+  "repo_id": "ResontraAI/voxedge-model-index",
+  "updated_at": "2026-08-13",
+  "publication_policy": "The public index may describe candidates and immutable non-identity packages, but it never contains recordings, embeddings, speaker indexes, private voices, secrets, or unreviewed weights.",
+  "entries": [
+    {
+      "id": "qwen3-06b-int4-ort",
+      "task": "text_llm",
+      "artifact_repo_id": "ResontraAI/voxedge-qwen3-06b-int4-ort",
+      "package_state": "ready_not_uploaded",
+      "hub_revision": null,
+      "planned_visibility": "public",
+      "identity_artifacts_allowed": false,
+      "blockers": ["Hub upload and remote hash verification"]
+    },
+    {
+      "id": "pocket-tts-english-int8-onnx",
+      "task": "tts",
+      "artifact_repo_id": "ResontraAI/voxedge-pocket-tts-english-int8-ort",
+      "package_state": "planned_benchmark",
+      "hub_revision": null,
+      "planned_visibility": "public",
+      "identity_artifacts_allowed": false,
+      "blockers": ["selective acquisition", "runtime review and binding", "native-to-ONNX parity", "consented fixed-voice review", "latency, quality, memory, and soak evidence"]
+    },
+    {
+      "id": "voxtream2-cuda-streaming",
+      "task": "tts",
+      "artifact_repo_id": "ResontraAI/voxedge-voxtream2-cuda",
+      "package_state": "planned_benchmark",
+      "hub_revision": null,
+      "planned_visibility": "public",
+      "identity_artifacts_allowed": false,
+      "blockers": ["eligible CUDA host", "native benchmark", "prompt deletion and lifecycle tests", "redistribution attribution review"]
+    },
+    {
+      "id": "streamvoiceanon-int8-cpu",
+      "task": "voice_conversion",
+      "artifact_repo_id": "ResontraAI/voxedge-streamvoiceanon-int8-ort",
+      "package_state": "blocked_release_gates",
+      "hub_revision": null,
+      "planned_visibility": "public",
+      "identity_artifacts_allowed": false,
+      "blockers": ["component redistribution review", "consented speech-quality and privacy evaluation", "physical x86 and CUDA measurements"]
+    },
+    {
+      "id": "rvc-v2-ort",
+      "task": "voice_conversion",
+      "artifact_repo_id": "ResontraAI/voxedge-rvc-v2-ort",
+      "package_state": "blocked_missing_authorized_artifacts",
+      "hub_revision": null,
+      "planned_visibility": "private_or_gated",
+      "identity_artifacts_allowed": false,
+      "blockers": ["authorized target checkpoint", "ContentVec and RMVPE acquisition", "native-to-ONNX parity", "speaker-specific distribution rights"]
+    },
+    {
+      "id": "beatrice-v2-runtime",
+      "task": "voice_conversion",
+      "artifact_repo_id": "ResontraAI/voxedge-beatrice-v2-runtime",
+      "package_state": "blocked_external_runtime_and_terms",
+      "hub_revision": null,
+      "planned_visibility": "private_or_gated",
+      "identity_artifacts_allowed": false,
+      "blockers": ["provider runtime and checkpoint access", "provider redistribution terms", "provider-authorized identity", "runtime parity and benchmark evidence"]
+    }
+  ]
+}