From 67db320ee673510cea5ac9e3eafe95a35a33ac65 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Sat, 12 Sep 2026 16:06:11 +0000
Subject: [PATCH] fix(audio-cpp): forward voice reference transcripts

Saved voices send ref_text, but Fish Audio requires reference_text.
Derive the canonical parameter while preserving explicit overrides.
Both TTS modes use the shared builder.

Add regression cases and document the parameter alias.

Assisted-by: Codex:gpt-6
---
 backend/cpp/audio-cpp/generation_request.cpp  |  7 ++++
 .../audio-cpp/generation_request_ctest.cpp    | 35 +++++++++++++++++++
 docs/content/features/audio-cpp.md            |  6 ++++
 3 files changed, 48 insertions(+)

diff --git a/backend/cpp/audio-cpp/generation_request.cpp b/backend/cpp/audio-cpp/generation_request.cpp
index 805bf35d8..c0aa2b95b 100644
--- a/backend/cpp/audio-cpp/generation_request.cpp
+++ b/backend/cpp/audio-cpp/generation_request.cpp
@@ -135,6 +135,13 @@ build_tts_request(const backend::TTSRequest &request,
         task.options["language"] = request.language();
     }
 
+    // Saved voice profiles send ref_text; Fish Audio reads reference_text.
+    // Derive the alias before copying params so an explicit canonical key wins.
+    const auto reference_text = request.params().find("ref_text");
+    if (reference_text != request.params().end()) {
+        task.options["reference_text"] = reference_text->second;
+    }
+
     // LAST, so an explicit params entry wins over anything derived above. That
     // matters for "caption": a caller who sets params[caption] has named the
     // exact string they want, and it must not be overwritten by `instructions`.
diff --git a/backend/cpp/audio-cpp/generation_request_ctest.cpp b/backend/cpp/audio-cpp/generation_request_ctest.cpp
index e9b5d5106..a2fcce0e3 100644
--- a/backend/cpp/audio-cpp/generation_request_ctest.cpp
+++ b/backend/cpp/audio-cpp/generation_request_ctest.cpp
@@ -375,6 +375,40 @@ static void test_tts_language_and_params() {
           "tts params: an explicit param overrides the derived caption");
 }
 
+static void test_tts_reference_transcript() {
+    backend::TTSRequest request;
+    request.set_text("New speech to generate.");
+    request.set_voice("reference.wav");
+    (*request.mutable_params())["ref_text"] = "The saved voice transcript.";
+
+    const auto task = build_tts_request(request, clip(24000, 1));
+    check(option_or(task.options, "reference_text", "") ==
+              "The saved voice transcript.",
+          "tts reference: saved transcript reaches Fish Audio's option");
+    check(option_or(task.options, "ref_text", "") ==
+              "The saved voice transcript.",
+          "tts reference: original transcript parameter is preserved");
+    check(task.text_input->text == "New speech to generate.",
+          "tts reference: transcript does not replace synthesis text");
+
+    (*request.mutable_params())["reference_text"] = "Explicit transcript.";
+    const auto explicit_task = build_tts_request(request, clip(24000, 1));
+    check(option_or(explicit_task.options, "reference_text", "") ==
+              "Explicit transcript.",
+          "tts reference: explicit canonical parameter wins over alias");
+
+    (*request.mutable_params())["reference_text"] = "";
+    const auto empty_task = build_tts_request(request, clip(24000, 1));
+    check(has_key(empty_task.options, "reference_text") &&
+              empty_task.options.at("reference_text").empty(),
+          "tts reference: explicit empty canonical parameter is preserved");
+
+    request.mutable_params()->clear();
+    const auto missing_task = build_tts_request(request, clip(24000, 1));
+    check(!has_key(missing_task.options, "reference_text"),
+          "tts reference: no transcript is invented when none was supplied");
+}
+
 static void test_sound_generation_minimal() {
     backend::SoundGenerationRequest request;
     request.set_text("a distant thunderstorm");
@@ -562,6 +596,7 @@ int main() {
     test_tts_empty_language_is_not_a_language();
     test_tts_clip_and_instructions();
     test_tts_language_and_params();
+    test_tts_reference_transcript();
     test_sound_generation_minimal();
     test_sound_generation_full();
     test_transform_text_absent();
diff --git a/docs/content/features/audio-cpp.md b/docs/content/features/audio-cpp.md
index f3a7ce4be..f1adca749 100644
--- a/docs/content/features/audio-cpp.md
+++ b/docs/content/features/audio-cpp.md
@@ -217,6 +217,12 @@ voice conversion from the same weights.
 
 ## Family notes
 
+- **Fish Audio voice cloning**: save a reference clip with its transcript in the
+  Voice Library, then select **Use in Text to Speech**. The backend accepts
+  `params.ref_text` as an alias for `params.reference_text` in both ordinary and
+  streaming speech requests. If you supply both parameters, `reference_text`
+  takes precedence. For direct requests with a reference file in `voice`, supply
+  its transcript in one of these parameters.
 - **Supertonic**: use the `orig` GGUF package, whose weights are f32. The f16 package was
   observed to reach `ggml_concat` with mismatched operand types and take the backend
   process down with `SIGABRT` on the first request, rather than returning an error.