CN8 is an AI gateway: a single proxy layer that gives you access to AI capabilities — chatbots with RAG, multi-agent orchestration, LLM completions, dubbing, TTS, media generation, and production-grade video/audio processing — all through one consistent API with unified auth, billing, and usage tracking.
Transcript & Video Understanding
ai-transcript
Transcribe a video or audio file, then derive metadata, chapters, quizzes, scene captions and translations from the resulting subtitle.
The pipeline has two halves. First transcribe the media — that call is async and returns subtitle URLs. Everything after it takes the subtitle text you got back (or any VTT/SRT you already have) and derives something new from it, so you can run those steps without re-transcribing.
POST transcript-transcribe: async — returns a job_id; poll /v2/jobs/{job_id} for the subtitle URLs
Fetch the VTT or SRT file and pass its contents as subtitle_content to the steps below
transcript-metadata and transcript-quiz answer immediately; transcript-chapters, transcript-caption and transcript-translate are async
subtitle_content is the file, not a URL
The derive endpoints take the raw VTT/SRT text in the request body, not a link to it. Download the subtitle from the transcribe result first, then send its contents.
