菜单
Text-to-speech generation using Qwen3-TTS via FAL API
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Align text to audio timestamps using Qwen3-ForcedAligner (~30ms precision)
Full pipeline from manga panels to animated video. Two audio modes: dialogue (Qwen3-TTS + karaoke captions) or music (ElevenLabs + rolling lyrics).
Burn karaoke captions into video using FFmpeg ASS subtitles (~20s for 16s video)
Generate multi-panel manga from character reference and story beats
Generates original background music using Google's Music Generation API. Creates soundtracks matched to scene mood and timing.
Concatenates video clips and optionally adds background music using FFmpeg.
| name | Qwen3-TTS |
| description | Text-to-speech generation using Qwen3-TTS via FAL API |
| triggers | ["Generate speech audio from dialogue","Multi-character voice synthesis","TTS for manga dialogue"] |
Generate high-quality speech audio from text using Qwen3-TTS.
from skills.qwen_tts import QwenTTS
tts = QwenTTS()
# Single line
result = await tts.generate_speech("Hello world!")
# result.audio_path, result.duration_seconds
# Multi-character dialogue
results = await tts.generate_dialogue([
("Mochi", "Hi there! What's that?"),
("Hero", "It's a treasure map!"),
])
QwenTTS.generate_speech()async def generate_speech(
text: str,
output_path: Path = None,
voice_embedding: Optional[Path] = None,
style_prompt: Optional[str] = None,
) -> TTSResult
QwenTTS.generate_dialogue()async def generate_dialogue(
dialogue_lines: list[tuple[str, str]],
character_voices: dict[str, Path] = None,
output_dir: Path = None,
) -> list[TTSResult]
Voice embeddings can be created using the FAL voice cloning API.
Pass a .safetensors file path to voice_embedding parameter.