Text-to-speech using Xiaomi's MiMo-V2-TTS model. Supports emotional style control, Chinese dialects (Northeastern/Sichuan/Cantonese/Taiwanese), role-playing voices, and singing synthesis.
https://api.xiaomimimo.com/v1/v1/chat/completions (NOT /audio/speech)mimo-v2-ttsMIMO_API_KEY env varMiMo TTS uses the Chat Completions endpoint with special requirements:
system role allowed (returns error)assistant role message (the text to synthesize)user message = style/voice instructionsassistant message = text to be spokenchoices[0].message.audio.data contains base64-encoded audiobash
python3 <skill_dir>/scripts/mimo_tts.py \
--text "Hello, world!" \
--output /tmp/openclaw/tts_output.mp3 \
[--style "cheerful tone"] \
[--speed 1.0] \
[--format mp3] \
[--api-key YOUR_KEY]
Set MIMO_API_KEY environment variable or pass --api-key.
ParameterRequiredDescription--text✅Text to synthesize (recommended < 5000 chars)--output✅Output audio file path--style❌Natural language style description--speed❌Speech rate 0.5–2.0 (default 1.0)--format❌mp3/wav/pcm/opus/flac (default mp3)--api-key❌API Key (overrides env var)
--style "speak in Cantonese" / "Sichuan dialect" / "Taiwanese accent"--style "happy and excited" / "sad and gentle" / "start happy then turn melancholic"--style "news anchor" / "gentle older sister"--style "sing it"--style "Northeastern dialect, enthusiastic and bold"