fix(mappings): update voice mappings for consistency, add missing aud…

CHANGELOG.md

@@ -4,6 +4,10 @@ Notable changes to this project will be documented in this file.
 
 Per-PR attribution and contributor credits are published automatically on the corresponding GitHub release page; this file is the curated, human-readable summary.
 
+## [v0.6.0] - Unreleased
+### Fixed
+- OpenAI voice aliases pointed at legacy v0.19 voicepacks that sound degraded on the v1.0 model. Added the proper v1.0 `bf_isabella` and repointed `nova` (`bf_v0isabella` -> `bf_isabella`), `alloy`, `ash`, `coral`, `echo` to their v1.0 voices. The `v0*` voices stay available by explicit name. (#479)
+
 ## [v0.5.0] - 2026-06-06
 ### Added
 - `POST /dev/unload` release model from VRAM without stopping container; lazy reload on next request. For freeing a shared GPU while idle. Reclaim scale with load (~0.7 GB; ~1.6 GB via long-form test on 4060Ti). (#474)

VERSION

@@ -1 +1 @@
-0.5.0
+0.6.0-rc1

api/src/core/openai_mappings.json

@@ -6,13 +6,13 @@
         "gpt-4o-mini-tts": "kokoro-v1_0"
     },
     "voices": {
-        "alloy": "am_v0adam",
-        "ash": "af_v0nicole",
-        "coral": "bf_v0emma",
-        "echo": "af_v0bella",
+        "alloy": "am_adam",
+        "ash": "af_nicole",
+        "coral": "bf_emma",
+        "echo": "af_bella",
         "fable": "af_sarah",
         "onyx": "bm_george",
-        "nova": "bf_v0isabella",
+        "nova": "bf_isabella",
         "sage": "am_michael",
         "shimmer": "af_sky"
     }

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "kokoro-fastapi"
-version = "0.5.0"
+version = "0.6.0-rc1"
 description = "FastAPI TTS Service"
 readme = "README.md"
 requires-python = ">=3.10"