download-audio
Download Simulation Audio
Download audio for $ARGUMENTS.
Single Simulation
coval simulations audio <simulation_id> -o recording.wav
This downloads the audio file with a progress bar.
Bulk Download (All from Run)
Step 1: List Simulations with Audio
coval simulations list --run-id <run_id> --format json | \
jq -r '.[] | select(.has_audio == true) | .simulation_id'
Step 2: Download Each
for sim_id in $(coval simulations list --run-id <run_id> --format json | jq -r '.[] | select(.has_audio == true) | .simulation_id'); do
coval simulations audio $sim_id -o "${sim_id}.wav"
done
Step 3: Organize
Suggest organizing by test case:
mkdir -p audio/<run_id>
# Download files into organized directory
Audio URL Only
To get the URL without downloading:
coval simulations audio <simulation_id>
This prints the presigned URL (valid for 1 hour).
Notes
- Audio is only available for voice agent simulations
- URLs expire after 1 hour
- Format is typically WAV or MP3
- Files include both agent and simulated caller audio
More from coval-ai/coval-external-skills
onboard
>
14launch-run
Launch a Coval evaluation run against an AI agent. Use when user wants to start an evaluation, test an agent, or run simulations.
12coval-resources
Comprehensive overview of ALL Coval platform resources, their hierarchy, relationships, API endpoints, and ID formats. Use when user asks about Coval resources, data model, how things relate, what endpoints exist, or needs context about the platform structure before making API calls.
12quick-eval
Full evaluation workflow - launch a run, watch progress, and summarize results. Use for end-to-end agent testing.
12watch-run
Monitor a Coval run's progress with live updates. Use when user wants to check run status or wait for completion.
12review-llm-annotations-and-improve-prompt
Calculate agreement between human ground truth and machine labels for a text LLM judge metric, then analyze transcripts and reviewer notes to propose an improved metric prompt. One metric at a time.
12