feat(tts): add Fish Audio as a text-to-speech provider

Registry entry plus one config-driven FORMAT_HANDLERS handler. The model id
travels in an HTTP `model` header rather than the JSON body, and the voice is
a reference_id (preset or cloned voice model).

Closes #2411

open-sse/handlers/ttsProviders/genericFormats.js

@@ -51,6 +51,25 @@ async function huggingface({ baseUrl, apiKey, text, modelId }) {
   return responseToBase64(res, "wav");
 }
 
+// Fish Audio: model travels in an HTTP header, the voice is a reference_id, returns binary
+async function fishAudio({ baseUrl, apiKey, text, modelId, voiceId }) {
+  const res = await fetch(baseUrl, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      "Authorization": `Bearer ${apiKey}`,
+      "model": modelId || "s2.1-pro-free",
+    },
+    body: JSON.stringify({
+      text,
+      format: "mp3",
+      ...(voiceId ? { reference_id: voiceId } : {}),
+    }),
+  });
+  if (!res.ok) await throwUpstreamError(res);
+  return responseToBase64(res, "mp3");
+}
+
 // Inworld: Basic auth, JSON { audioContent }
 async function inworld({ baseUrl, apiKey, text, modelId, voiceId }) {
   const res = await fetch(baseUrl, {
@@ -166,4 +185,5 @@ export const FORMAT_HANDLERS = {
   tortoise,
   openai: openaiCompat,
   "minimax-tts": minimaxTts,
+  "fish-audio": fishAudio,
 };

open-sse/providers/registry/fish-audio.js

@@ -0,0 +1,31 @@
+// Fish Audio TTS — the model id travels in an HTTP `model` header rather than the
+// JSON body, and the voice is a reference_id (a cloned or preset voice model).
+export default {
+  id: "fish-audio",
+  alias: "fish",
+  display: {
+    name: "Fish Audio",
+    icon: "record_voice_over",
+    color: "#1E9BF0",
+    textIcon: "FA",
+    website: "https://fish.audio",
+    notice: {
+      apiKeyUrl: "https://fish.audio/app/api-keys/",
+    },
+  },
+  category: "apikey",
+  authType: "apikey",
+  serviceKinds: ["tts"],
+  ttsConfig: {
+    baseUrl: "https://api.fish.audio/v1/tts",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "fish-audio",
+    models: [
+      { id: "s2.1-pro-free", name: "S2.1 Pro Free" },
+      { id: "s2.1-pro", name: "S2.1 Pro" },
+      { id: "s2-pro", name: "S2 Pro" },
+      { id: "s1", name: "S1" },
+    ],
+  },
+};

open-sse/providers/registry/index.js

@@ -119,6 +119,7 @@ import p116 from "./tokenrouter.js";
 import p117 from "./selfhosted-stt.js";
 import p118 from "./selfhosted-tts.js";
 import p119 from "./selfhosted-embedding.js";
+import p120 from "./fish-audio.js";
 
 export default [
   p0,
@@ -239,4 +240,5 @@ export default [
   p117,
   p118,
   p119,
+  p120,
 ];