feat: add minimax tts support (#1043)

open-sse/handlers/ttsProviders/genericFormats.js

@@ -1,6 +1,7 @@
 // Generic config-driven TTS handlers — dispatched by ttsConfig.format.
 // Each handler accepts { baseUrl, apiKey, text, modelId, voiceId } and returns { base64, format }.
 import { responseToBase64, throwUpstreamError } from "./_base.js";
+import minimaxTts from "./minimax.js";
 
 // Hyperbolic: POST { text } → { audio: base64 }
 async function hyperbolic({ baseUrl, apiKey, text }) {
@@ -164,4 +165,5 @@ export const FORMAT_HANDLERS = {
   coqui,
   tortoise,
   openai: openaiCompat,
+  "minimax-tts": minimaxTts,
 };

open-sse/handlers/ttsProviders/minimax.js

@@ -0,0 +1,59 @@
+import { Buffer } from "node:buffer";
+
+function hexToBase64(audioHex) {
+  const clean = typeof audioHex === "string" ? audioHex.trim() : "";
+  if (!clean) throw new Error("MiniMax TTS returned no audio");
+  if (clean.length % 2 !== 0 || !/^[0-9a-f]+$/i.test(clean)) {
+    throw new Error("MiniMax TTS returned invalid audio");
+  }
+  return Buffer.from(clean, "hex").toString("base64");
+}
+
+// MiniMax T2A HTTP: returns hex-encoded audio in non-streaming mode.
+export default async function minimaxTts({ baseUrl, apiKey, text, modelId, voiceId }) {
+  const res = await fetch(baseUrl, {
+    method: "POST",
+    headers: { "Content-Type": "application/json", "Authorization": `Bearer ${apiKey}` },
+    body: JSON.stringify({
+      model: modelId || "speech-2.8-hd",
+      text,
+      stream: false,
+      language_boost: "auto",
+      output_format: "hex",
+      voice_setting: {
+        voice_id: voiceId || "English_expressive_narrator",
+        speed: 1,
+        vol: 1,
+        pitch: 0,
+      },
+      audio_setting: {
+        sample_rate: 32000,
+        bitrate: 128000,
+        format: "mp3",
+        channel: 1,
+      },
+    }),
+  });
+
+  const rawText = await res.text();
+  let data = {};
+  if (rawText) {
+    try { data = JSON.parse(rawText); } catch { data = {}; }
+  }
+
+  const baseResp = data.base_resp || data.baseResp || {};
+  const statusCode = Number(baseResp.status_code ?? baseResp.statusCode ?? 0);
+  const statusMessage = baseResp.status_msg || baseResp.statusMsg || data.message || "";
+
+  if (!res.ok) {
+    throw new Error(statusMessage || rawText || `MiniMax TTS error (${res.status})`);
+  }
+  if (statusCode !== 0) {
+    throw new Error(statusMessage || "MiniMax TTS upstream error");
+  }
+
+  return {
+    base64: hexToBase64(data.data?.audio),
+    format: data.extra_info?.audio_format || data.extraInfo?.audioFormat || "mp3",
+  };
+}