Lexonia Video Lens — Video Transcript, Translation & Summary
Pricing
from $30.00 / 1,000 audio transcriptions
Transcribe and translate any video from a URL — YouTube, TikTok, Vimeo, Bilibili (B站) & Douyin (抖音). Real speech-to-text: works when captions are off, auto-detects the language. Transcript, translation, SRT/VTT subtitles, optional AI summary. Works in Claude & ChatGPT via MCP.
One or more video URLs — YouTube, TikTok, Vimeo, Bilibili (B站), or Douyin (抖音). Each video is transcribed in its original language (via captions or AI speech-to-text) and summarized in the languages you choose below.
[ "https://www.youtube.com/watch?v=dQw4w9WgXcQ"]Optional. Paste a whole channel or creator profile and the Actor pulls its recent videos automatically — no need to list each video. Supported: YouTube (channel/@handle), Bilibili (space.bilibili.com/…), Douyin (douyin.com/user/…). Order and count are controlled by the two fields below. (For TikTok/Vimeo channels, paste video URLs above for now.)
[]How many videos to pull from each channel/profile above. Kept modest by default because each video is transcribed. Raise it for a bigger batch (watch your cost cap below).
For channel/profile inputs: process the NEWEST videos first (default — the creator's latest uploads) or the OLDEST first (read a creator from the beginning).
Turn ON to get a quick preview: how many videos, the expected cost you'll pay, and the approximate time — WITHOUT transcribing anything. Great for checking a whole channel before you commit. Turn OFF to run for real. NOTE FOR AI ASSISTANTS (Claude/ChatGPT via MCP): when the input is a whole channel or several videos, run with estimateOnly=true FIRST, show the user the returned estimatedCostUsd range, and only run again with estimateOnly=false once they approve.
The language SPOKEN in the video. Leave on 'Auto-detect' (recommended) — the Actor figures it out and reports a confidence score. This is NOT the language you want the text in: to get the text in another language, use 'Translate full transcript into' below. (If you pick a language here that differs from what is spoken, the Actor treats it as the language you want and translates into it.)
Turn on ONLY if a summary was asked for. Generates an AI summary of each transcript in the languages below (billed per summary language). Off by default: a plain run returns the transcript (or the translation, if requested) and nothing you didn't ask for.
Pick one or more languages to produce the summary in. 'Original' keeps the video's own language; add any others to translate the summary into. A Chinese video with [Original, English] returns both a Chinese and an English summary. Covers the languages of the world's major economies.
[ "original"]The language(s) you want the text IN. 'Transcribe this video in Ukrainian' = put Ukrainian here. Produces a COMPLETE, word-for-word translation of the entire transcript into each language — not a summary — and puts the first one in the result's output field. Ideal for reading a foreign-language video in full (e.g. a Chinese Douyin/Bilibili video in English). Billed per language.
[]AI used for summaries and translations. 'openai' (default) is BUILT IN — no key needed. 'anthropic' (Claude), 'deepseek' and 'qwen' need YOUR OWN API key in the field below; DeepSeek/Qwen work inside mainland China where OpenAI/Claude are blocked.
Optional. Leave blank to use the bundled model (summary billed per the Store price). Or provide your own key for the provider above to run on your own account. Never stored.
API key for AI speech-to-text on platforms without captions (Bilibili, Douyin, TikTok). Uses OpenAI — leave blank if your summary provider is already OpenAI (that key is reused).
Advanced: a Bilibili SESSDATA cookie can unlock higher-quality audio or member-only videos. Optional — most public videos work without it.
Choose the AI model quality for summaries and translations. 'Premium' (default) uses a stronger model for noticeably better, more accurate summaries and translations — best for foreign-language and Chinese video. 'Standard' is a faster, cheaper downgrade if you want to save. (A 'Summary model' override below decides which model actually runs, but selecting Premium still applies the premium surcharge.)
Override the default model. Defaults: gpt-4o-mini (OpenAI), claude-haiku-4-5 (Anthropic), deepseek-chat (DeepSeek), qwen-plus (Qwen).
Advanced: override the endpoint for any OpenAI-compatible provider (e.g. a self-hosted model or a regional endpoint). Leave blank to use the provider default.
How each summary should be formatted.
Which files to save to the run's key-value store (Storage tab) — all free. TXT = one plain-text file per video with the transcript, plus one per full translation (e.g. transcript-youtube-.Ukrainian.txt) — the file names are listed in each result's textFiles field. JSON is LLM-ready, CSV for spreadsheets, Markdown/PDF for a shareable document. The dataset itself is always structured and natively exportable too.
[ "json", "csv", "txt"]Optional. Generate timed subtitle files for each video, saved to the run's storage. Available where timing data exists: YouTube (captions), TikTok and Bilibili (speech-to-text). Billed per video.
[]