The Earnings Call Transcript API turns two messy sources into clean JSON: SEC 8-K filings parsed straight from EDGAR, and speaker-tagged earnings call transcripts. Give it a ticker and a dataType (filings, transcripts, or both), or run a full-text keyword search across every US filer.

What it returns

For filings: item codes and item names, the extracted press release, isolated guidance sentences, a sentiment score, and the source EDGAR url. For transcripts: participants with roles, prepared remarks, and analyst question-and-answer pairs matched to the executives who answered. Every record links back to its filing, so claims stay checkable. No audio, and no 10-K or 10-Q statements; this is an events and calls feed, not a fundamentals database.

Example Tasks & Use Cases

AAPL earnings call transcript - the speaker-tagged Apple call as JSON, with NVDA, TSLA, MSFT, META, AMZN and more on the examples tab.

SEC EDGAR 8-K filings API by ticker - recent parsed 8-Ks for any company, item codes tagged.

8-K item codes, guidance and sentiment - the full parsed structure of a filing in one record.

Material weakness screener - full-text search across all US filers for red-flag accounting language.

Going concern warning screener - surface filers flagging doubt about staying solvent.

Guidance withdrawal screener - catch companies pulling their forward guidance.

Material events watchlist - with onlyNew set, scheduled runs return only fresh filings, turning item-code filters into event trackers.

Cybersecurity incident monitor - Item 1.05 disclosures as a feed.

Executive departure tracker - Item 5.02 leadership changes across filers.

Earnings call Q&A dataset for LLM and RAG - pre-matched qaPairs as a training-ready corpus.

Earnings guidance monitor - track forward-looking statements over time.

Works with MCP

The Actor runs over the Model Context Protocol, so Claude, Claude Code, and Cursor can call it as a tool mid-conversation. Ask "summarize Apple's latest 8-K and pull its guidance language" and the answer runs against the real filing instead of the model's memory. No scraping code to write.

Pricing

Pay per event: one parsed filing or one structured transcript per record, no start fee. About one cent for a hundred records, so a quarterly refresh of a 50-ticker watchlist costs roughly that.

Keywords & Topics

earnings call transcript api, sec edgar api, 8-k filing parser, earnings call sentiment analysis, sec full-text search, edgar 8-k monitor, earnings call q and a dataset, financial data api, sec filings api, mcp finance tool for AI agents.