fix(minimax): mark tts output voice-compatible

CHANGELOG.md

@@ -86,6 +86,7 @@ Docs: https://docs.openclaw.ai
 - Providers/OpenAI-compatible: skip null or non-object streaming chunks from custom providers instead of failing the turn after partial output. Fixes #51112.
 - Providers/OpenAI-compatible: treat singular MLX-style `finish_reason: "tool_call"` as tool use instead of a provider error. Fixes #61499.
 - Providers/ElevenLabs: omit the MP3-only `Accept` header for PCM telephony synthesis, so Voice Call requests for `pcm_22050` no longer receive MP3 audio. Fixes #67340. Thanks @marcchabot.
+- Providers/MiniMax TTS: mark MP3 output voice-compatible for Telegram voice-note delivery. Fixes #63540.
 - Providers/Microsoft TTS: keep allowlisted bundled speech providers discoverable even when another speech plugin has already registered, so Edge/Microsoft TTS is available alongside OpenAI. Fixes #62117 and #66850.
 - Providers/Microsoft TTS: honor legacy `messages.tts.providers.edge` voice settings after normalizing Edge TTS to the Microsoft provider. Fixes #64153.
 - macOS Talk Mode: retry failed local ElevenLabs stream playback through gateway `talk.speak` before falling back to the system voice, so configured ElevenLabs voices still play when streaming playback fails. Fixes #65662.

extensions/minimax/speech-provider.test.ts

@@ -240,7 +240,7 @@ describe("buildMinimaxSpeechProvider", () => {
 
       expect(result.outputFormat).toBe("mp3");
       expect(result.fileExtension).toBe(".mp3");
-      expect(result.voiceCompatible).toBe(false);
+      expect(result.voiceCompatible).toBe(true);
       expect(result.audioBuffer.toString()).toBe("fake-audio-data");
 
       expect(mockFetch).toHaveBeenCalledOnce();

extensions/minimax/speech-provider.ts

@@ -227,7 +227,7 @@ export function buildMinimaxSpeechProvider(): SpeechProviderPlugin {
         audioBuffer,
         outputFormat: "mp3",
         fileExtension: ".mp3",
-        voiceCompatible: false,
+        voiceCompatible: true,
       };
     },
   };