submit also accepts --input-json (inline JSON, @file, or - for stdin); explicit flags override fields from the JSON. See Input JSON.
Submit Conversation
Submit a production conversation for evaluation. At least one input source is required (--transcript-file, --audio-file, --audio-url, or --upload-id); audio sources are mutually exclusive.
Returns the created conversation in
PENDING status. Poll coval uploaded-conversations get <id> to watch evaluation progress.
For audio files larger than a few megabytes, prefer
--audio-url or --upload-id over --audio-file — the request body is capped at 10 MB. Those routes carry audio out of band and accept up to 250 MB.List Uploaded Conversations
Output columns: ID, STATUS, EXTERNAL ID, AUDIO, OCCURRED AT
Get Uploaded Conversation
Returns full conversation details as JSON including transcript, status, agent and persona references, progress, and metadata.
Patch Uploaded Conversation
Attach audio to an existing conversation or add metadata keys. Metadata is additive only: the API rejects a key that already has a value.Download Audio
Download or get the audio URL for a conversation recording.-o, a progress bar shows the download status.
List Metrics
List the current metric results for an uploaded conversation. If a metric has been re-scored, only its most recent result is listed.
Output columns: OUTPUT ID, METRIC ID, STATUS, VALUE, SUBVALUES
Get Metric Detail
Retrieve metric results for a conversation. The second argument accepts two ID types and the output adapts accordingly:- 26-char MetricOutput ULID — prints one row (the specific output).
- 22-char Metric definition ID — prints every output recorded for that metric on the conversation.
By MetricOutput ULID (one row):
Delete Conversation
Conversation Statuses
When using
--filter, use the underscore-separated enum values (e.g., status="IN_PROGRESS").