diff --git a/docs/asset-engine/services.yaml b/docs/asset-engine/services.yaml
index 96b7bd0..3eccf96 100644
--- a/docs/asset-engine/services.yaml
+++ b/docs/asset-engine/services.yaml
@@ -619,7 +619,7 @@ services:
       Trained 10M+ hours, dual-AR. Released March 2026. Heavy: ~240s compile
       warmup on cold start, ~realtime throughput once warm.
     category: tts
-    version: 3
+    version: 4
     host: irv-ml1
     lifecycle:
       stack: fish-s2
@@ -714,6 +714,9 @@ services:
           - Alice
           - Austin
           - Axel
+          - Beatrice
+          - Eleanor
+          - Imogen
           - Connor
           - Cora
           - Elena
@@ -739,15 +742,17 @@ services:
           - Thomas
         description: >
           Voice = a staged clone reference picked by name (THE working voice
-          path on this build; verified live 2026-06-01). 29 voices staged in
-          /worktank/fish-s2/references/: 28 from the dia library + glados.
-          Female voices: Abigail, Alice, Cora, Elena, Emily, Gianna, Jade,
-          Layla, Olivia (+ glados). Default Emily (female). Resolves to
-          <name>.wav + its <name>.txt transcript. Leave blank for the model's
-          default/random speaker. To add a voice: drop a clean 5–15s WAV (+
-          optional <name>.txt) into the references dir, then add the name here.
-          (Fish exposes no /voices API → this list is static; a list-endpoint
-          is the durable fix — see notes.)
+          path on this build; verified live 2026-06-01). 32 voices staged in
+          /worktank/fish-s2/references/: 28 from the dia library + glados + 3
+          British-female VCTK voices (Beatrice/Eleanor/Imogen). Default Emily.
+          Subtle British (Southern-England) female accents: Imogen (VCTK p225),
+          Eleanor (p228), Beatrice (p229) — consenting VCTK volunteers (CC BY
+          4.0), NOT modeled on or representing any public figure. Other female:
+          Abigail, Alice, Cora, Elena, Emily, Gianna, Jade, Layla, Olivia,
+          glados. Resolves to <name>.wav + optional <name>.txt transcript;
+          blank = model default/random speaker. To add: drop a clean 5–15s WAV
+          into the references dir + add the name here. (No /voices API → static
+          list; a list-endpoint is the durable fix — see notes.)
       - name: references
         type: json
         label: Custom clone (inline base64)