The documents that matter after an earnings release, as structured JSON: the word-for-word call transcript, an AI summary with reported metrics, and the calendar that tells you when the next one lands.
# 1. Scan a global watchlist for "agentic AI" mentions in Q1 2026
# → per-ticker mention counts across markets, in one request
curl -sG https://earningscalls.dev/api/v1/search/by_ticker \
-H "X-API-Key: ec_..." \
--data-urlencode 'q="agentic AI"' \
--data-urlencode 'tickers=NVDA,SAP,SHEL' \
--data-urlencode 'date_from=2026-01-01' \
--data-urlencode 'date_to=2026-04-30'
// example response · ~312 ms
{
"query": "\"agentic AI\"",
"tickers_scoped": 3,
"total_companies": 3,
"total_calls": 7,
"results_count": 3,
"results": [
{ "ticker": "NVDA", "company_name": "NVIDIA Corporation", "calls_matched": 4, "last_match_date": "2026-03-17T16:00:00.000Z" },
{ "ticker": "SAP", "company_name": "SAP SE", "calls_matched": 2, "last_match_date": "2026-04-23T21:00:00.000Z" },
{ "ticker": "SHEL", "company_name": "Shell plc", "calls_matched": 1, "last_match_date": "2026-02-05T14:30:00.000Z" }
]
}Four primitives that turn raw earnings calls into a clean dataset your strategy can consume.
Every segment pre-tagged. Five categories with verified counts: executive (826k), analyst (470k), operator (208k), attendee (33k), shareholder (4k). 93% carry the speaker's name.
GET /api/v1/speakers/:idSweep the live archive for phrases like "margin pressure" in one query. Boolean operators, exact phrases, ticker filters across global markets.
GET /api/v1/search?q=…Scan up to 500 tickers in a single request. Per-ticker counts, sector breakdown, last-match date — screen a global universe in one call.
GET /api/v1/search/by_tickerIncremental sync via since / after_id. Re-runnable, idempotent. New calls land within hours of the wire and flow straight into your pipeline.
GET /api/v1/transcripts/recentChange the ticker, click Run, see the actual response.
GET /api/v1/search?q=agentic AI&type=speakers&speaker_type=Executive&ticker=NVDA&limit=5
Read for free. Automate when you're ready. Cancel anytime.
Full access for builders and traders
For production apps and teams
High-volume production workloads
Coverage, query semantics, and what the data supports.
For the narrative side, yes: each call's AI summary extracts the reported metrics (revenue, EPS, guidance) management discussed, and the transcript is the full primary source. For filed statements (10-Q/10-K tables) pair us with a filings API - our earnings call API vs SEC filings API comparison explains when you need which.
Release timing comes from the earnings calendar API; the discussion of the release - the call - lands as a transcript minutes after it ends, with the AI summary following within the hour for S&P 500 names.
No - slides are not part of the API. In practice the transcript covers the spoken content of the deck, and the AI summary condenses the numbers management highlighted. If you specifically need PDFs of decks, investor-relations pages remain the source.
Everything is JSON over REST: transcripts as full text plus speaker-segment arrays, summaries as structured fields, calendar as flat rows. The transcript API and API reference document every schema.
What research professionals say about the data and the API.
“Excellent service. Comprehensive coverage of the sectors I wanted and the API is very easy to work with. Highly recommend.”
“Transcripts are accurate, and the API is very user friendly.”
“Connecting Claude through MCP to analyze earnings transcripts has never been easier.”
From the team that brought you the Earnings Calls API - same clean data, same fair pricing.
Pre-configured, industry-standard stock screeners - near real-time, refreshed every 5 minutes, no setup required.
Scans options activity across all US stocks - immediate email alerts the moment institutional-sized trades hit your watchlist.