Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

或改用 Fish Audio TTS · worldwonderer | DecimalAI

design mediaby worldwonderer

或改用 Fish Audio TTS

worldwonderer/video-voiceover

Source worldwonderer/video-recap-skills ↗License MIT

把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS（mimo-v2.5-tts）逐段生成语音，按时间窗动态适配语速并处理响度；输入输出时间线上的旁白，产出 tts_segments 与 tts_meta.json。旧版直接剪辑路径也可显式传入 narration_mapped.json。触发词：配音、语音合成、TTS、解说配音、 voiceover、text to speech、旁白配音。

SkillScore96Maintained

Automatic

AI Engineer pack

Last verified 8/27/2026

What it changes

Passed 23 of 24 test cases with the skill, and 6 of 24 without it.

Without skill24%

With skill96%

Checks it passed that the model alone missed

Sets TTS_WORKERS environment variable.
Sets TTS_TIMEOUT environment variable.
Requires narration field in every segment.

and 23 more in the full report

18 fixed6 passed either way1 still failing0 broke

Pass-rate lift: +72 pp
Tokens: -19%
Agent turns: 0%
Response time: -70%

Model gemini-3.6-flashMeasured 8/27/2026v224 of 25 cases passed with skill · 24 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/worldwonderer-video-voiceover/SKILL.md https://app.decimal.ai/s/worldwonderer-video-voiceover/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add worldwonderer-video-voiceover, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/worldwonderer-video-voiceover/ and pins it in .decimal/skills.lock

decimalai skills add worldwonderer-video-voiceover

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/worldwonderer-video-voiceover/SKILL.md https://app.decimal.ai/s/worldwonderer-video-voiceover/SKILL.md

Raw file: /s/worldwonderer-video-voiceover/SKILL.md ↗ · machine-readable summary at /s/worldwonderer-video-voiceover.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

在未指定 --tts-provider 且未设置环境覆盖变量时，直接对 work_dir/narration.json 运行配音生成工具，系统默认使用哪个 TTS 引擎服务？

What was checked, without and with the skill
Checked	Without skill	With skill
Selects mimo-v2.5-tts as the default engine.	Missed	Passed

case-07 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md70 lines6 filesincludes scripts

1. 定位

本技能读取带时间戳的旁白稿，为每一段生成独立音频，并把语音适配到对应时间窗，随后记录下游合成所需的放置元数据。默认引擎是 MiMo TTS（mimo-v2.5-tts）；也可显式选择 Fish Audio（默认模型 s2.1-pro-free）。

2. 环境要求

export MIMO_API_KEY=***  # 也可使用仅供 TTS 的 MIMO_TTS_API_KEY

# 或改用 Fish Audio TTS
export TTS_PROVIDER=fish-audio
export FISH_API_KEY=***
export FISH_TTS_REFERENCE_ID=<voice-model-id>  # 可选；覆盖内置“娱乐扒妹”音色

下面的 scripts/... 均相对于本技能目录。若执行器从仓库根目录启动，请给脚本路径加上本技能的绝对目录。脚本不从其他技能目录读取文件；外部输入仅限命令显式传入的稿件、音频、参数与 work_dir 产物。

3. 输入契约

默认输入为 work_dir/narration.json。每段必须包含 start、end 与 narration，可选字段包括 pause_after_ms 和 overlaps_speech。时间统一表示音频最终放置的输出时间线秒数。

编排式 cut 流程直接使用输出时间的 narration.json。只有旧版直接剪辑路径需要显式传入 narration_mapped.json。

4. 运行命令

python3 scripts/voiceover.py --work-dir <work_dir> --narration <narration.json> \
  [--tts-provider auto|mimo-tts|fish-audio] \
  [--mimo-voice 冰糖 | --voice-ref <reference-audio>]

单独运行且省略 --narration 时，默认读取 work_dir/narration.json。旧版路径如需映射后的稿件，必须显式传入：

python3 scripts/voiceover.py --work-dir <work_dir> \
  --narration <work_dir/narration_mapped.json>

Track record

Benchmark

23 / 24

test cases passed, vs 6 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/26/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

worldwonderer / video-recap-skills

skills/video-voiceover/SKILL.md

View on GitHub ↗

License MITImported 8/26/2026Version v2Bundled 5 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.