From 284ec5b4c405893bf9412ccf9bfbfc260720bf0d Mon Sep 17 00:00:00 2001
From: Vuong Hoang <vh@phasefinal.com>
Date: Mon, 1 Jun 2026 13:15:15 -0700
Subject: [PATCH] catalog(fish-s2): voice dropdown via reference_id (29 staged
 voices)

Staged 28 single-speaker dia voices + glados into /worktank/fish-s2/references/
(internal research use). Discovered the path-form references shape 500s on this
build; reference_id (by name) is the working voice path (verified live). So:
reference_id -> select 'Voice' with the 29 staged names (default Emily, female);
references demoted to advanced inline-base64 custom clones with the path->500
caveat documented. vram 10->24 (measured ~25GB in use); version 2->3.
---
 docs/asset-engine/services.yaml | 68 ++++++++++++++++++++++++++-------
 1 file changed, 54 insertions(+), 14 deletions(-)

diff --git a/docs/asset-engine/services.yaml b/docs/asset-engine/services.yaml
index db00f67..96b7bd0 100644
--- a/docs/asset-engine/services.yaml
+++ b/docs/asset-engine/services.yaml
@@ -619,11 +619,11 @@ services:
       Trained 10M+ hours, dual-AR. Released March 2026. Heavy: ~240s compile
       warmup on cold start, ~realtime throughput once warm.
     category: tts
-    version: 2
+    version: 3
     host: irv-ml1
     lifecycle:
       stack: fish-s2
-      vram_gb: 10
+      vram_gb: 24
       gpu_device_id: 1
     endpoint: http://10.100.79.3:8195/v1/tts
     method: POST
@@ -701,23 +701,63 @@ services:
         section: sampling
         required: false
         description: Omit for a random seed; a fixed integer repeats a take.
+      - name: reference_id
+        type: select
+        label: Voice
+        section: basic
+        optional: true
+        default: "Emily"
+        options:
+          - Abigail
+          - Adrian
+          - Alexander
+          - Alice
+          - Austin
+          - Axel
+          - Connor
+          - Cora
+          - Elena
+          - Eli
+          - Emily
+          - Everett
+          - Gabriel
+          - Gianna
+          - glados
+          - Henry
+          - Ian
+          - Jade
+          - Jeremiah
+          - Jordan
+          - Julian
+          - Layla
+          - Leonardo
+          - Michael
+          - Miles
+          - Olivia
+          - Ryan
+          - Taylor
+          - 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.)
       - name: references
         type: json
-        label: Voice References (clone)
+        label: Custom clone (inline base64)
         section: advanced
         optional: true
         description: >
-          Array of {audio: "/app/references/<file>.wav", text: "transcript"} for
-          zero-shot cloning. Files under /worktank/fish-s2/references/ on host.
-      - name: reference_id
-        type: text
-        label: Stored reference id
-        section: advanced
-        optional: true
-        description: >
-          Alternative to inline `references`: id of a server-stored reference
-          set (a folder under the server's references/). Leave blank to use
-          `references` or the default voice.
+          Power-use: zero-shot clone from a reference NOT in the staged library
+          — array of {audio: <base64-encoded WAV bytes>, text: "transcript"}.
+          IMPORTANT: `audio` must be base64 bytes, NOT a filesystem path (a path
+          returns HTTP 500 on this build). For staged voices use `reference_id`.
       - name: max_new_tokens
         type: number
         section: advanced