From 5c4784339cd72b729662356e53f2af885f464e25 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Sun, 31 May 2026 15:27:56 -0700 Subject: [PATCH] catalog(dia2): default to a working stable voice (fix undefined-ref 404) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reported: dia2-1b 404 'Reference audio file not found: undefined' when accepting defaults — voice_mode=clone with no clone_reference_filename made the UI submit the literal 'undefined'. Fix: voice_mode now defaults to clone AND clone_reference_filename defaults to Abigail.wav (a staged voice), so the out-of-box request is a valid, stable voice. Reproduced the 404 and verified the Abigail.wav path returns 200. Folded into v2 (not yet consumed downstream). --- docs/asset-engine/services.yaml | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/docs/asset-engine/services.yaml b/docs/asset-engine/services.yaml index 6f1139e..a9f379e 100644 --- a/docs/asset-engine/services.yaml +++ b/docs/asset-engine/services.yaml @@ -1285,17 +1285,20 @@ services: type: select label: Voice mode section: basic - options: [single_s1, single_s2, dialogue, clone] - default: single_s1 + options: [clone, single_s1, single_s2, dialogue] + default: clone description: > - Canonical default single_s1. Unconditioned modes (single_s1/s2, - dialogue) sample a RANDOM speaker each call — gender varies. For a - STABLE voice, set this to clone and pick a clone_reference_filename. + Defaults to `clone` -> a stable predefined voice (clone_reference_filename + below, default Abigail.wav). The unconditioned modes (single_s1/s2, + dialogue) sample a RANDOM speaker each call (gender varies) — pick one + only if you want that. NOTE: voice_mode=clone REQUIRES a real + clone_reference_filename; an empty/"undefined" value 404s. - name: clone_reference_filename type: select label: Voice (clone reference) section: basic optional: true + default: "Abigail.wav" source_url: http://10.100.79.3:8200/get_reference_files source_jsonpath: $[*] description: > @@ -1446,17 +1449,20 @@ services: type: select label: Voice mode section: basic - options: [single_s1, single_s2, dialogue, clone] - default: single_s1 + options: [clone, single_s1, single_s2, dialogue] + default: clone description: > - Canonical default single_s1. Unconditioned modes (single_s1/s2, - dialogue) sample a RANDOM speaker each call — gender varies. For a - STABLE voice, set this to clone and pick a clone_reference_filename. + Defaults to `clone` -> a stable predefined voice (clone_reference_filename + below, default Abigail.wav). The unconditioned modes (single_s1/s2, + dialogue) sample a RANDOM speaker each call (gender varies) — pick one + only if you want that. NOTE: voice_mode=clone REQUIRES a real + clone_reference_filename; an empty/"undefined" value 404s. - name: clone_reference_filename type: select label: Voice (clone reference) section: basic optional: true + default: "Abigail.wav" source_url: http://10.100.79.3:8202/get_reference_files source_jsonpath: $[*] description: >