Audio
TTS + 词级对齐From its SKILL.md
npx -y skills add ChaosRealmsAI/NextFrame --skill audioAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 24 stars24 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 3 commands, including `nf-guide audio` and 2 more.
SKILL.md
0.7 KB, 253 tokens by cl100k_base, as published. Nobody here has run it
audio · TTS + 词级对齐
NextFrame audio 流程(TTS 合成 → WhisperX 字级对齐 → karaoke.html)。
推进状态机
第一步必做:
Bash("nf-guide audio") # 读 state machine
核心命令:
Bash("nf-tts batch <batch.json> --dir <out_dir>")· 批次合成 mp3 + timeline.json + srtBash("nf-tts <text> -v <voice>")· 单条合成
voice 选:
- edge 免费: zh-CN-XiaoxiaoNeural(晓晓) / YunxiNeural(云希) / YunyangNeural(云扬)
- volcengine 付费(seed-tts-2.0): 需
-b volcengine
产物
- mp3 音频
- timeline.json(whisperx 词级时间戳 · 卡拉 OK 字幕同步)
- srt 字幕
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.