hindcast

Use cases & endpoints

Earnings call transcripts API — searchable with citations

The most quotable sentence on an earnings call is rarely in the script. It is an answer to the analyst who asked the question management hoped to avoid, delivered with qualifications that matter and that summaries reliably discard.

Working with transcripts as flat documents loses that structure. Prepared remarks and Q&A get blended, speaker attribution is inconsistent, and a search returns whole calls when what you needed was one exchange.

Hindcast structures each call with prepared remarks and Q&A as separate sections, speakers and roles attached, and passage-level timestamps so a quote can be located in the recording. Companies resolve through the entity graph, which means a transcript search can be scoped by the same identifiers as a filings query — and a passage can be cited with its call, speaker and moment rather than pasted without provenance.

hindcast — session

preview

hindcast> find the Q&A exchange about guidance on the last call

→ tool: transcripts_search { entity:"...", section:"qa", query:"guidance" }

matching exchanges with analyst and executive attribution

source: call transcript with prepared remarks and Q&A separated

Preview of the shape of an answer — endpoints open to the waitlist first.

What's covered

Join the waitlist — this page's dataset is already selected.

Need this one?votes for Global Media Transcripts
Optional — helps us build in the right order. All skippable.

Role

Company

Datasets you need

Questions

Why separate prepared remarks from Q&A?

Because they are different kinds of evidence. Prepared remarks are written, reviewed and legally checked; Q&A is live. Treating them as one block makes it impossible to distinguish a rehearsed claim from an unscripted admission.

Can I track language changes across quarters?

Yes — running the same query across consecutive calls returns comparable passages, which is how a subtle shift in how management describes a trend becomes visible without reading every transcript in full.

Join the waitlist. Vote the roadmap. First in, first served.

← Back to the data catalog