Add the AI read to a breakdown
label_breakdownAdd the AI read of every shot to a finished free breakdown. This SPENDS the user's coins: price it with estimate_breakdown on the breakdown's source_url (from get_breakdown or list_breakdowns) and pass that total as expected_total — if the price changed, nothing is spent. Without expected_total, a host that can ask the person confirms the price with them; any other host is answered the price. Poll get_breakdown (a host that runs tool tasks waits for it itself).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| funding | No | who pays: personal (the person's own coins) or team (their team's pool — only when the person allowed this connection to spend team coins and the team approved this app). Omit to use the payer the person chose when connecting | |
| purpose | No | why the clip is being read — omit to keep the breakdown's | |
| transcribe | No | also transcribe the speech (costs transcribe_coins) | |
| label_model | No | a model id from estimate_breakdown's label_models — omit for the default | |
| prompt_lang | No | the language the recreate prompts are written in — omit to keep the breakdown's | |
| breakdown_id | Yes | a succeeded breakdown that has no AI read yet | |
| expected_total | No | the total coins estimate_breakdown quoted for this choice — omit it only when the host confirms prices with the person itself |