Summary

Adds Krisp VIVA Turn (pipecat's KrispVivaTurn, VIVA SDK turn detection v3 / Tt API) as a selectable turn_stop_strategy in the cascade pipeline, alongside the existing LocalSmartTurnAnalyzerV3. Unlike Smart Turn (which analyzes audio in batches when VAD detects a pause), KrispVivaTurn processes audio frame-by-frame in real time, using the VAD's speech flag as an external signal.

Changes

• turn_config.py — new krisp_viva_turn branch in create_turn_stop_strategy(). Forwards threshold / frame_duration_ms to KrispTurnParams and model_path / api_key / sample_rate to the KrispVivaTurn constructor (all fall back to env vars). The pipecat module is imported lazily because it hard-requires the proprietary krisp_audio SDK — environments without it are unaffected until the strategy is selected.
• config.py + .env.example — document the new strategy and required env vars (KRISP_VIVA_TURN_MODEL_PATH, KRISP_VIVA_API_KEY).
• test_turn_config.py — 4 new tests covering the branch (happy path, case-insensitivity, tuning-param routing, constructor-param routing) via an injected fake krisp module.
• Bumped simulation_version 2.0.1 → 2.0.2 (affects benchmark outputs).

Enabling it

Krisp is a licensed SDK, not a PyPI package, so it is intentionally not in pyproject.toml. To run this strategy you provision it at runtime:

1. Download from the Krisp developer portal (developers.krisp.ai): the VIVA UAR Python SDK zip and the Turn-Taking models zip. Unzip both.
2. Install the wheel matching your interpreter's Python version and architecture from the SDK's dist/ folder — e.g. macOS x86_64 / Py3.11:

   uv pip install .../krisp-viva-uar-python-sdk-<ver>/dist/krisp_audio-<ver>-cp311-cp311-macosx_11_0_x86_64.whl

   (Pick arm64 vs x86_64 to match python -c "import platform; print(platform.machine())".)
3. Point env vars at the model + your license key, then select the strategy:

   export KRISP_VIVA_TURN_MODEL_PATH=/path/to/krisp-viva-tt-models/krisp-viva-tp-v3.kef
   export KRISP_VIVA_API_KEY=<license key>
   eva --domain airline --model.llm gpt-5-mini --model.turn-stop-strategy krisp_viva_turn

Optional tuning via EVA_MODEL__TURN_STOP_STRATEGY_PARAMS — threshold (default 0.5) and frame_duration_ms (default 20; one of 10/15/20/30/32).

Network: the SDK validates its license against sdkapi.krisp.ai and reports usage to analytics.krisp.ai. Both must be reachable; a WAF/proxy that blocks them will fail license validation. Eval keys are time-limited and metered per minute.

Deployment (toolkit / Docker)

The runtime image is linux/amd64, so it needs the Linux wheel from the same SDK download — krisp_audio-<ver>-cp311-cp311-linux_x86_64.whl (ships alongside the macOS wheels). The wheel + .kef model should be baked into the image from an internal artifact store (not committed to git), with KRISP_VIVA_API_KEY injected as a runtime secret and egress to the two Krisp hosts allowlisted. Tracked as follow-up.

Testing

• 27/27 test_turn_config.py unit tests pass; ruff + version-bump checks pass; no new mypy errors.
• Live end-to-end validated (macOS, cascade pipeline): a full multi-turn airline conversation ran with turn_stop_strategy=krisp_viva_turn; the SDK initialized, loaded the model, and produced 90 real end-of-turn predictions (model probabilities 51–99%, end-of-turn latencies ~0.1 ms–1.5 s, mostly ~100–300 ms). Turn-taking was driven entirely by Krisp.
• Also confirmed the lazy-import boundary: when krisp_audio is absent, selecting the strategy fails with a clean, actionable error and no other strategy is affected.