Smart Turn v2

audio-stt

Detects when a user is done speaking. Pairs with an STT model for real-time voice pipelines.

MODALITIES

audio

Smart Turn v2 (pipecat-ai/smart-turn-v2) is a audio-stt model from Pipecat. Pricing via AIgateway: $0.0021 per minute. Call it via https://api.aigateway.sh/v1/audio/transcriptions — set model="pipecat-ai/smart-turn-v2". Best for: Voice agents, IVR, Meeting assistants.

model · pipecat-ai/smart-turn-v2family · Smart Turn

Use this model

model: pipecat-ai/smart-turn-v2

curl https://api.aigateway.sh/v1/audio/transcriptions \
  -H "Authorization: Bearer $AIGATEWAY_API_KEY" \
  -F model="pipecat-ai/smart-turn-v2" \
  -F file="@audio.mp3"

curl https://api.aigateway.sh/v1/audio/transcriptions \ -H "Authorization: Bearer $AIGATEWAY_API_KEY" \ -F model="pipecat-ai/smart-turn-v2" \ -F file="@audio.mp3"

Capabilities

Strengths

Sub-200ms turn-end detection
Reduces awkward voice-agent pauses

Use cases

Voice agentsIVRMeeting assistants

Pricing

Per minute$0.0021

Turn-detection, not transcription

You pay pass-through · 5% applied at credit top-up, not per-call.

See API example →Compare API reference See usage ranking →

Collections

More audio models →More from Pipecat →Frontier models →Free-tier models →

API schema

Call Smart Turn v2 from any OpenAI SDK

POST https://api.aigateway.sh/v1/audio/transcriptions·Content-Type: multipart/form-data·Auth: Bearer sk-aig-...

Request body

json

# multipart/form-data — use curl -F or SDK file upload
model="pipecat-ai/smart-turn-v2"
file=@audio.mp3
response_format=json    # or "verbose_json", "text", "srt", "vtt"
language=en             # optional

Response

json

{
  "text": "Hello from AIgateway.",
  "language": "en",
  "duration": 1.82
}

Quickstart

from openai import OpenAI
client = OpenAI(base_url="https://api.aigateway.sh/v1", api_key="sk-aig-...")

with open("audio.mp3", "rb") as f:
    r = client.audio.transcriptions.create(model="pipecat-ai/smart-turn-v2", file=f)
print(r.text)

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?

Detects when a user is done speaking. Pairs with an STT model for real-time voice pipelines. It is a audio-stt model from Pipecat, accessible via AIgateway's OpenAI-compatible API at slug pipecat-ai/smart-turn-v2.

How much does Smart Turn v2 cost via AIgateway?

$0.0021 per minute of audio. Pass-through plus a 5% platform fee applied at top-up.

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 — no. Tool calling — no. Vision — no. JSON mode — no. Prompt caching — no.

What are the best use cases for Smart Turn v2?

Voice agents, IVR, Meeting assistants. Key strengths: Sub-200ms turn-end detection; Reduces awkward voice-agent pauses.

Can I bring my own Pipecat API key (BYOK)?

Yes. Attach a Pipecat key in your AIgateway dashboard and this model flips to pass-through — you pay Pipecat directly and AIgateway waives the 5% platform fee on those calls.