voxarena 0.1.2

An evaluation arena for realtime voice agents.

An evaluation arena for realtime voice agents.

VoxArena is a reproducible benchmarking harness for realtime voice agents. Run the same scripted conversation across Gemini Live, OpenAI Realtime, and other Pipecat-supported providers — and compare them apples-to-apples on latency, tool-call accuracy, and hallucinations.

Drop it into your CI pipeline, your dev loop, or the bundled control panel.

---

🚀 CI & Pipeline Integration

VoxArena ships a voxarena CLI designed for headless use in your build pipeline. It returns a non-zero exit code when metrics fall below thresholds you define, and emits JUnit XML for native CI reporting.

pip install voxarena

voxarena run \
  --provider gemini \
  --script ./script/utterances.yaml \
  --min-tool-accuracy 0.9 \
  --max-hallucinations 0 \
  --max-avg-ttfa-ms 1500 \
  --output result.json \
  --junit voxarena.xml
# exit 0 if every threshold passes, 1 otherwise

Compare two providers in one shot

voxarena compare \
  --gemini-model gemini-3.1-flash-live-preview \
  --openai-model gpt-realtime-2 \
  --num-turns 5 \
  --min-tool-accuracy 0.9 \
  --output compare.json

GitHub Actions

- name: Voice agent regression check
  env:
    GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
  run: |
    pip install voxarena
    voxarena run --provider gemini \
      --min-tool-accuracy 0.92 --max-hallucinations 0 \
      --junit voxarena.xml --quiet

- uses: mikepenz/action-junit-report@v4
  if: always()
  with:
    report_paths: voxarena.xml

Subcommands

Command	What it does
voxarena run	Single-provider scripted run; exits 0/1 against thresholds.
voxarena compare	Runs Gemini and OpenAI in parallel against the same script.
voxarena report	Generates a markdown comparison report from past runs.

Run voxarena <command> --help for the full flag set.

---

Features

• 🎙️ Provider-agnostic agent — one Pipecat pipeline drives every provider; swap models without re-implementing your agent
• 🔁 Scripted conversations — multi-turn YAML scripts with pre-recorded WAV inputs and expected tool calls / response content
• 📊 Automated scoring — tool-call correctness, response matching, hallucination counts, time-to-first-audio, interruption-stop latency
• 🆚 Side-by-side comparisons — run multiple providers in parallel against the same script
• 🗄️ Persistent run history — JSON manifests on disk, indexed in SQLite
• 🖥️ Web control panel — React UI to launch runs, watch live status, browse results, and edit scripts
• 🧩 Extensible — add a new provider by implementing one adapter class

Architecture

Local Dev (with UI)

git clone https://github.com/simkeyur/vox-arena.git
cd vox-arena
cp .env.example .env  # add GOOGLE_API_KEY / OPENAI_API_KEY

python3 -m venv .venv && source .venv/bin/activate
pip install -e .

uvicorn voxarena.main:app --reload --port 8000

Then in another terminal:

cd ui && npm install && npm run dev

Open the control panel at http://localhost:5173.

Bring Your Own Agent

The demo ships with the "Saffron Leaf" restaurant agent so you can run end-to-end on day one. To evaluate your own:

1. Replace the system prompt and tool schemas in voxarena/agent.py
2. Implement (or stub) your tools in voxarena/tools.py
3. Re-record script/audio/*.wav and update script/utterances.yaml to reflect your real workload
4. Run the arena as normal — every provider gets scored against your scripts

Scripted Conversations

Conversations live in script/utterances.yaml. Each turn pairs an utterance id with an expect block describing the correct tool call and/or response content:

- id: u04
  text: "Are you open on Sundays?"
  expect:
    tool: get_hours
    args:
      day: sunday
    response_contains:
      - "closed"

The harness plays script/audio/{id}.wav into the pipeline and scores the agent's actual tool calls and transcript against expect.

Configuration

Variable	Description
GOOGLE_API_KEY / OPENAI_API_KEY	Provider credentials
GEMINI_MODEL / OPENAI_MODEL	Realtime model under test
GEMINI_EVAL_MODEL / OPENAI_EVAL_MODEL	Cheaper text models for grading
PORT	FastAPI server port
BASE_DIR	Override workdir (CLI: --workdir)

Contributing

To add a new provider: implement an adapter in voxarena/providers/ following the pattern in gemini.py / openai.py, wire it into voxarena/harness.py and voxarena/config.py, and open a PR.

For bugs and feature requests, please open an issue.

License

MIT.