Smoke Tests and Benchmarking

Once your deployment is running, you can test it using the following commands. Ensure you have network access to your service via port-forwarding or an ingress.

List Voices

curl "http://<your-host>:<port>/voices" \
  -H "Cartesia-Version: 2025-04-16" \
  -H "X-API-Key: $CARTESIA_API_KEY" | jq '.'

Text-to-Speech

curl -X POST "http://<your-host>:<port>/tts/bytes" \
  -H "Cartesia-Version: 2025-04-16" \
  -H "X-API-Key: $CARTESIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "sonic-2",
    "transcript": "Hello, this is a test of the Cartesia text-to-speech API.",
    "voice": {
      "mode": "id",
      "id": "bf0a246a-8642-498a-9950-80c35e9276b5"
    },
    "output_format": {
      "container": "wav",
      "encoding": "pcm_f32le",
      "sample_rate": 44100
    },
    "language": "en"
  }' > output.wav

Benchmarking

cartesia-kube includes a k6 load testing suite under benchmarking/ for measuring TTS performance metrics like TTFA and latency. Start with the closed-loop WebSocket entry point, which holds a fixed number of concurrent streams open. MODEL_ID must match a deployed worker’s model and VOICE_ID must be a voice available in your deployment.

cd cartesia-kube/benchmarking

# Smoke test — one connection, one request, 3 seconds
k6 run -e WS_SCHEME=wss -e API_HOST=<your-domain> -e API_PORT=443 \
  -e MODEL_ID=<model> -e VOICE_ID=<voice> \
  -e VUS=1 -e CONTEXTS_PER_CONN=1 \
  -e RAMP_DURATION=0s -e DURATION=3s \
  tts_websocket_closed.ts

# Sustained load — ramp to 10 connections (4 contexts each) over 30s, hold 1 min
k6 run -e WS_SCHEME=wss -e API_HOST=<your-domain> -e API_PORT=443 \
  -e MODEL_ID=<model> -e VOICE_ID=<voice> \
  -e VUS=10 -e CONTEXTS_PER_CONN=4 \
  -e RAMP_DURATION=30s -e DURATION=1m \
  tts_websocket_closed.ts

See benchmarking/README.md for the SSE and bytes transports, open-loop mode, and the full list of environment variables and reported metrics.

Overview

Deployments

Guides

Performance

Smoke Tests and Benchmarking

List Voices

Text-to-Speech

Benchmarking

​List Voices

​Text-to-Speech

​Benchmarking

List Voices

Text-to-Speech

Benchmarking