models/Pipecat-ai/Smart-Turn-V2
PA
Pipecat-ai

Smart-Turn-V2

classification
Compare

An open source, community-driven, native audio turn detection model in 2nd version

MODALITIES
text
RELEASED
2025-08-04

Smart-Turn-V2 (pipecat-ai/smart-turn-v2) is a classification model from Pipecat-ai, released 2025-08-04. Pricing via AIgateway: $0.0003 per minute. Capabilities: streaming, async. Call it via https://api.aigateway.sh/v1/classifications — set model="pipecat-ai/smart-turn-v2".

model · pipecat-ai/smart-turn-v2

Use this model

model: pipecat-ai/smart-turn-v2
curl https://api.aigateway.sh/v1/classifications \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"pipecat-ai/smart-turn-v2","state":"Help! My payouts have been failing for 3 days.","questions":{"is_urgent":{"type":"noul","instructions":"Does this convey urgency?","criteria":{"true":"Explicitly time-sensitive","false":"No urgency expressed"}}}}'
API schema

Call Smart-Turn-V2 from any OpenAI SDK

POST https://api.aigateway.sh/v1/classifications·Content-Type: application/json·Auth: Bearer sk-aig-...

Request body

json
{
  "model": "pipecat-ai/smart-turn-v2",
  "state": "Help! My payouts have been failing for 3 days.",  // a string, or an object
  "questions": {
    "is_urgent": {
      "type": "noul",                                   // noul | choice | score
      "instructions": "Does this convey urgency?",
      "criteria": { "true": "Explicitly time-sensitive", "false": "No urgency expressed" }
    },
    "department": {
      "type": "choice",
      "instructions": "Which team should handle this?",
      "criteria": { "billing": "Payments, refunds", "technical": "Bugs, outages", "sales": "Pricing, upgrades" }
    },
    "frustration": {
      "type": "score",
      "instructions": "How frustrated is the customer?",
      "criteria": ["Calm", "Frustrated", "Very angry"]
    }
  }
}

Response

json
{
  "answers": {
    "is_urgent": { "type": "noul", "noul": 0.95 },
    "department": {
      "type": "choice",
      "choice": "billing",
      "confidence": 0.8,
      "probabilities": { "billing": 0.87, "technical": 0.13, "sales": 0 }
    },
    "frustration": {
      "type": "score",
      "score": 1.04,
      "confidence": 0.94,
      "legend": { "0": "Calm", "1": "Frustrated", "2": "Very angry" },
      "probabilities": { "0": 0, "1": 0.96, "2": 0.04 }
    }
  },
  "model": "pipecat-ai/smart-turn-v2",
  "usage": { "input_tokens": 426, "output_tokens": 73, "billing_unit": "token" }
}

Quickstart

import os, requests

r = requests.post(
    "https://api.aigateway.sh/v1/classifications",
    headers={"Authorization": f"Bearer {os.environ['AIGATEWAY_API_KEY']}"},
    json={
        "model": "pipecat-ai/smart-turn-v2",
        "state": "Help! My payouts have been failing for 3 days.",
        "questions": {
            "is_urgent": {"type": "noul", "instructions": "Does this convey urgency?",
                          "criteria": {"true": "Explicitly time-sensitive", "false": "No urgency expressed"}},
            "department": {"type": "choice", "instructions": "Which team should handle this?",
                           "criteria": {"billing": "Payments, refunds", "technical": "Bugs, outages"}},
        },
    },
)
print(r.json()["answers"])

Errors

401authentication_errorInvalid or missing API key
402insufficient_creditsWallet empty (PAYG only)
404not_foundUnknown model or endpoint
429rate_limit_errorOver per-minute limit — see Retry-After header
500server_errorUpstream provider failed (retryable)
503service_unavailableUpstream saturated (retryable)
Full docs →API reference →OpenAPI spec →llms.txt →

Frequently asked questions

What is Smart-Turn-V2?
An open source, community-driven, native audio turn detection model in 2nd version It is a classification model from Pipecat-ai, accessible via AIgateway's OpenAI-compatible API at slug pipecat-ai/smart-turn-v2.
How much does Smart-Turn-V2 cost via AIgateway?
$0.0003 per minute of audio, billed pass-through.
How do I call Smart-Turn-V2 from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to "pipecat-ai/smart-turn-v2". The request and response shapes match OpenAI exactly.
Does Smart-Turn-V2 support streaming, tool calling, vision, and JSON mode?
Streaming — yes. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.
Can I bring my own Pipecat-ai API key (BYOK)?
Yes. Attach a Pipecat-ai key in your AIgateway dashboard and this model flips to pass-through — you pay Pipecat-ai directly and AIgateway adds no platform fee on those calls.