Earnings Call Transcripts
get_transcriptsGet earnings call transcripts for a company. Returns paragraph-by-paragraph text (speaker, timestamp, text), paginated via paragraph_limit/paragraph_cursor since a full call can be tens of thousands of tokens.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"symbol": "<symbol>"
},
"name": "get_transcripts"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Target language for translated text fields (BCP 47, e.g. "ja", "zh-Hant"); English or omitted = no translation | |
| limit | No | Maximum number of transcripts to return (default: all) | |
| fields | No | Comma-separated list of GraphQL field names to include; omitted = curated default set | |
| symbol | Yes | Stock ticker symbol | |
| paragraph_limit | No | Maximum transcript paragraphs per page; omitted = curated default (25). A full call's `text` is returned as paginated paragraphs, not one giant blob | |
| paragraph_cursor | No | Opaque continuation token from a previous response's paragraphs `pageInfo.endCursor`; omitted = first page |