Telegram Channel Scraper + AI Translate & Summarize
Pricing
from $1.00 / 1,000 post saveds
Export posts from any public Telegram channel: text, date, views, reactions, links, media, forwards. No login or bot token. Optional AI with your own API key (OpenAI, Claude, Gemini...): translate, summarize, entities, sentiment. Monitoring mode returns only new posts.
Public channel usernames or links. Accepts durov, @durov, t.me/durov or https://t.me/s/durov. Private channels and groups are not supported.
Newest posts first. Scraping stops at this number (or earlier if you set a start date).
Oldest post date to include, YYYY-MM-DD (UTC). Leave empty for no limit.
Newest post date to include, YYYY-MM-DD (UTC). Leave empty for up to now.
Keep only posts containing at least one of these words (case-insensitive). Leave empty to keep all posts. You pay only for posts that are saved.
Add photo/video/document info and preview URLs to each post.
Remembers the newest post of each channel. Schedule this Actor (e.g. hourly or daily) and every run returns — and charges for — only posts published since the previous run.
Use a different name for each separate monitor (e.g. "crypto-news", "competitors"). Only letters, numbers and dashes.
For every post with text: detected language, full translation, one-sentence summary, up to 3 topics, people/organizations/locations and sentiment. Uses YOUR OWN AI API key below — you pay your AI provider directly for tokens (usually cents per 1,000 posts).
Any OpenAI-compatible API. Tip: a free Google AI Studio key works with "Google Gemini". Choose "Custom" for your own gateway, Together, Mistral, a local server, etc.
Stored encrypted by Apify, never logged or saved to results. Only used to call the provider you chose.
Model name at your provider. Leave empty for the default: OpenAI gpt-4o-mini, OpenRouter openai/gpt-4o-mini, Google Gemini gemini-3.5-flash-lite (works with a free AI Studio key), DeepSeek deepseek-chat. Required for Anthropic, Groq and Custom — use a fast, cheap model.
Only for provider "Custom": the OpenAI-compatible base URL, e.g. https://api.together.xyz/v1
Language for translations, summaries and topics.
Safety limit. Each page holds about 20 posts. Increase it when a keyword filter skips many posts.
Polite pause between page requests. Lower is faster but more likely to be rate-limited.
