Create Replay Run
Start a replay run against one or more voice clip sets.
Plays each clip set’s recorded caller turns back byte-identical, placing one call per clip set and repetition, for inbound and outbound agents alike. Returns 202 while the calls run asynchronously; poll List Replay Runs for progress.
Authorizations
Use Tuner API key (tr_api_...) or user session token. Find your API key in Workspace Settings > API Keys.
Path Parameters
Tuner's internal numeric ID for the agent.
Workspace ID. Find this in Workspace > General Settings.
Body
Request to launch a deterministic replay run against one or more voice clip sets.
IDs of the voice clip sets to replay, 1 to 10 sets.
1 - 10 elementsNumber of times to replay each clip set (1-20). Defaults to 1. len(voice_clip_set_ids) * repeat_count must be at most 20.
1 <= x <= 202
Maximum length of each replayed call, in minutes (1-12). Defaults to 3. A clip set whose worst-case call duration exceeds this is rejected.
1 <= x <= 123
IDs of PASS_FAIL evals to grade the replayed calls with. Omit, null or [] means no evals are run (a latency-only run).
IDs of call intents to detect on the replayed calls.
Overrides for the replay's turn-timing. Omitted fields use their defaults.
Response
Successful Response
The simulation run that was just started.
ID of the new simulation run.
Number of test scenarios created so far. 0 for Run AI-Generated Scenarios, because generation is asynchronous; the full count for replay runs and runs from saved scenarios.
Whether the run was accepted.
ID of the caller persona used. Null for replay runs.
The caller persona used. Null for replay runs.
ID of the simulation profile used, if one was given.
Name of the simulation profile used, if one was given.
Copy of the profile's fields as they were when the run started.
ID of the background-noise environment used, if one was given.
Gain applied to the background noise, if noise was used.
The background-noise environment used, if one was given.