Audio Models

doubao-tts — ByteDance Doubao speech synthesis model. Supports multiple languages, voices, and highly natural streaming audio output, suitable for news broadcasts and audiobooks.
elevenlabs-dialogue — ElevenLabs eleven_v3 multi-voice dialogue: assign a different voice per line (up to 10) and render the whole conversation in one shot. Supports audio tags like [giggling], [whispers] — great for character dialogue, podcasts, and short skits. Before picking a voice, you can search for the right one via elevenlabs-search.
elevenlabs-music — ElevenLabs music_v1 model — generates 10–300s original music from a natural-language prompt. Good for BGM, ads, and short-video soundtracks.
elevenlabs-search — Search the ElevenLabs voice library by keyword, source, and category. Returns a playable preview for each matched voice so you can pick the right one before running TTS. Search with ONE short English descriptor (deep / young / narrative); extra words narrow the match and full sentences usually return nothing.
elevenlabs-sfx — ElevenLabs text-to-sound model — generates 1–22s short sound effects from a description. Suitable for foley, ambience, alerts, and game SFX.
elevenlabs-tts — ElevenLabs eleven_v3 text-to-speech with 12 curated multilingual voices and stability/similarity/style controls. Great for dubbing, audiobooks, and character dialog. Before picking a voice, you can search for the right one via elevenlabs-search.
elevenlabs-voice-clone — ElevenLabs Instant Voice Cloning (IVC). Upload a clean voice sample to clone a custom voice usable with ElevenLabs TTS.
gemini-2.5-tts — Gemini-powered high-quality text-to-speech. Supports bilingual (EN/CN) and various emotional voices.
keling-sfx — Sound effect generation model: supports text-to-SFX and matching SFX/BGM for reference videos. Suitable for foley, ambient sounds, and short video audio completion.
keling-tts — Text-to-speech model (TTS), supports language, voice, speed, and output format settings. Suitable for dubbing, audiobooks, and voice broadcasts.
kling-audio-clone — Custom voice (Kling), cloned voice used for dubbing or binding to subjects.
qwen-audio-clone — Alibaba Bailian qwen3-tts voice cloning. Upload a clean voice sample to clone a custom voice usable in subsequent TTS calls.
qwen-tts — Alibaba Bailian qwen3-tts text-to-speech. Choose from curated system voices (including dialects) or design a custom voice from a natural-language description.
suno-music — Suno V5.5 music generation. Inspiration mode (auto lyrics) or custom mode (manual style/title/lyrics). Generates music with or without vocals, with fine-grained controls over style weight, weirdness and audio weight.
vidu-audio-clone — Clone a real human voice and use it to read the specified text.