Get transcript
Full transcript of a conversation as text with speaker names and optional timestamps.
MCP tool otter_read → get_transcript
read
Returns the whole transcript as plain text, one paragraph per speaker turn, in the order spoken. Timestamps are on by default; switch them off for shorter text. The call works for conversations you own and for ones shared with you. A transcript holds what every participant said, so treat its content as theirs too.
Parameters
| Name | Type | Description |
|---|---|---|
| conversation_id string required | string | Conversation ID from list_conversations or search_transcripts. |
| include_timestamps boolean | boolean | Add a timestamp to each paragraph. Default: true. |
tools/call
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "otter_read",
"arguments": {
"operation": "get_transcript",
"arguments": {
"conversation_id": "conversation_8c41d2"
}
}
}
}Example response
{
"content": [
{
"type": "text",
"text": "{ ... same JSON as structuredContent ... }"
}
],
"structuredContent": {
"conversation_id": "cv_7f3a91",
"format": "txt",
"content": "Sam Lee 00:00\nThanks for joining. Let's start with the two pricing options.\n\nJane Doe 00:09\nWe prefer a flat rate if it keeps approvals simple.\n\nSam Lee 00:18\nUnderstood, I'll send a revised quote this week."
},
"isError": false
}