How to analyze Douyin content in bulk for creator teams
Creator teams run Subtitle Transcriber, Audio Lens and Video Content Studio over exported Douyin files in one local batch on Windows 10/11.
Skills in this bundle
Video Content Studio
Content video production copilot (task-mode x top_n; LLM-orchestrated). (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Music Lens
Media task skill: Music Lens (sub-variant mode x top_n; LLM-orchestrated). (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Music Composer
Media task skill: Music Composer (sub-variant mode x top_n; LLM-orchestrated). (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Audio Lens
Media task skill: Audio Lens (sub-variant mode x top_n; LLM-orchestrated). (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Voice Producer
Media task skill: Voice Producer (sub-variant mode x top_n; LLM-orchestrated). (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Subtitle Transcriber
Media task skill: Subtitle Transcriber (sub-variant mode x top_n; LLM-orchestrated). (Action Co-pilot: generates next-best-actions (actions.json), follow-up tasks and calendar reminders on top of the analysis — what to act on today.)
Export your Douyin videos and audio into one folder on Windows, then run Subtitle Transcriber for transcripts and timecodes, Audio Lens for speaker, emotion and key points, and Video Content Studio for video analysis and script breakdowns. Nexus Runner 1.0.10 calls all six skills on your own machine, so the footage never leaves the PC, and each run costs 1 to 5 Nex.
- Six skills cover transcription, audio analysis, video analysis, music analysis, voice production and composing, over one batch of material.
- Everything runs through Nexus Runner 1.0.10 on your own machine; Windows 10/11 x64 only, and the media stays local.
- Each skill outputs structured files by mode and top_n, infers the type from the input, and does not invent missing data.
- Priced per run in Nex: Video Content Studio and Music Composer 1 Nex each; Subtitle Transcriber, Audio Lens, Voice Producer and Music Lens 5 Nex each.
- The free tier gives 200 Nex a month, reset at the start of each month; Pro is CNY 49/month with 3000 Nex; Enterprise is CNY 299/month with 50000 Nex.
What this workflow actually does
This is not one vague short-video assistant. It is six skills, each with a defined input and output, applied in order to Douyin material you have already exported to your machine. Subtitle Transcriber turns speech into subtitles, verbatim transcripts or timecodes. Audio Lens reads speaker, emotion and key points out of the voice track. Video Content Studio handles video analysis, script writing, subtitle transcription, adaptation and production planning. Music Lens judges the structure, mood and genre of your background music. Voice Producer and Music Composer turn those findings back into usable audio and score plans. All six are skills, meaning schema-bounded single-step operations, as opposed to an agent that orchestrates multiple steps. They read the files you already hold; they do not log into Douyin and do not drive any third-party account for you.
Six steps for one batch of Douyin material
How the three approaches differ
| MCP Nexus | Manual work | Generic cloud AI | |
|---|---|---|---|
| Batch handling | One folder, with transcription, audio analysis and video analysis in a single pass | Play each clip, type the transcript, copy the notes by hand | Usually one file at a time, uploaded and prompted individually |
| Where the media goes | Skills run on your Windows machine, so video and audio stay local | Files scattered across laptops and cloud drives, versions tracked by filename | Material has to be uploaded to a third-party server first |
| Shape of the output | Structured files keyed by mode and top_n, reusable and comparable | Meeting-notes documents with a different field layout per person | A block of text in a chat window that still needs tidying |
| Pricing model | Per run in Nex; free tier 200 Nex a month reset monthly, Pro CNY 49/month with 3000 Nex | Person-hours, and rework is charged again | Per seat subscription, paid whether or not it runs |
| Boundaries | Works only on files you exported; it does not manage platform accounts | Someone logs in and downloads clip by clip | You still have to obtain the files yourself |
Real use cases
FAQ
Can these skills pull videos straight off Douyin?
No. All six skills work only on files you have already exported to a local folder. They do not log into Douyin and do not operate any third-party platform account. You handle the export, then the skills handle transcription and analysis in bulk.
How much Nex does a batch of videos cost?
Pricing is per run: Video Content Studio and Music Composer are 1 Nex each, while Subtitle Transcriber, Audio Lens, Voice Producer and Music Lens are 5 Nex each. The free tier gives 200 Nex a month reset at the start of each month, Pro is CNY 49/month with 3000 Nex, and Enterprise is CNY 299/month with 50000 Nex.
Does my footage get uploaded anywhere?
No. The skills run on your own machine, and both the source media and the results stay on your local disk. You need Windows 10/11 x64 and Nexus Runner 1.0.10.
What if I have no subtitle files yet?
That is fine. Run Subtitle Transcriber first with mode set to subtitles, verbatim transcript or timecodes, then feed the result into Audio Lens and Video Content Studio so every later step shares the same text input.
Can it write the next script and score after the analysis?
Yes. Video Content Studio in script writing or adaptation mode produces the new script, Voice Producer in audio processing or voice arrangement mode plans the voice track, and Music Composer in composing or arranging mode plans the score, all based on the structured findings from the earlier steps.