Turn Detection

Timing matters. VAD detects silence; turn detection reads meaning so your agent knows when to respond and when to keep listening.

Echo Turn Detector

Zero Runtime’s turn detector is Echo, a server-hosted model passed to your Pipeline as the turn_detector. It is exposed through the Zero Runtime Inference Gateway via the unified TurnDetector class (model="echo-small" or model="echo-large"). No model is downloaded or loaded on your machine; authentication requires ZRT_AUTH_TOKEN. Choose echo-small for speed or echo-large for accuracy.

VAD detects that speech is happening; the turn detector decides when the turn is over.

How It Works

As the user speaks, VAD detects the speech and STT produces a transcript. After each user utterance, the latest transcript is sent to the Inference Gateway, where the selected Echo model (echo-small or echo-large) classifies the turn into one of four states:

State	Meaning
`Complete`	The user has finished their turn.
`Incomplete`	The user is still mid-sentence or not finished yet.
`Backchannel`	A short acknowledgement (e.g. “uh-huh”, “okay okay”).
`Wait`	The user wants the agent to hold (e.g. “wait a minute”, “hold on”).

Models

Both models share the same four-state classification; they differ only in the latency/accuracy trade-off:

Provider	Model Name	Model ID
Zero Runtime	Echo Small	`echo-small`
Zero Runtime	Echo Large	`echo-large`

model="echo-small": the lowest-latency model, optimized for the fastest possible turn detection. Best when responsiveness matters most.
model="echo-large": a higher-accuracy model that trades a little latency for better classification. Best when accuracy matters more than raw speed.

Supported Languages

Both echo-small and echo-large support 12 languages: English, Hindi, Gujarati, Marathi, Tamil, Telugu, Urdu, Bengali, French, German, Italian, and Spanish.

Usage

Set your auth token, then construct TurnDetector with the echo-small or echo-large model:

# Set ZRT_AUTH_TOKEN in your environment.

from zrt.plugins import TurnDetector

# Fastest, lowest latency
turn_detector = TurnDetector(model="echo-small")

# Higher accuracy
turn_detector = TurnDetector(model="echo-large")

Performance

Benchmarked on the TURNS2K dataset against a leading third-party turn-detection model, referred to here as Baseline. Each sample is labeled Complete (the user has finished speaking) or Incomplete (the user is still speaking).

Metric	Echo-Small	Echo-Large	Baseline
Accuracy	93.60%	96.20%	61.13%
Recall (Complete)	97.31%	96.50%	32.83%
Specificity	88.91%	95.81%	96.83%
F1 Score (Complete)	0.9443	0.9659	0.4851

Results are measured on the benchmark dataset described above, on samples labeled Complete or Incomplete. Performance may vary depending on language, deployment configuration, user behavior, and application requirements.

Choosing a Model

Model	Latency	Accuracy	Best For
Echo Small	Lowest	High	Lowest-latency, responsive agents
Echo Large	Low	Highest	Highest accuracy

End-of-Utterance Handling

End-of-Utterance (EOU) handling decides when the pipeline treats the user as finished speaking. In ADAPTIVE mode, the wait timeout adjusts based on confidence scores, so the agent waits longer when the user is hesitant and responds faster when intent is clear. Configure it with EOUConfig in your pipeline options:

from zrt import Pipeline, EOUConfig

pipeline = Pipeline(
    # ... other config
    eou_config=EOUConfig(
        mode="ADAPTIVE",
        min_max_speech_wait_timeout=[0.5, 0.8]
    )
)

Parameter	Type	Default	Description
`mode`	`"DEFAULT"` \| `"ADAPTIVE"`	`"DEFAULT"`	`ADAPTIVE` uses LLM confidence to adjust wait time.
`min_max_speech_wait_timeout`	`[float, float]`	`[0.5, 0.8]`	Min and max wait time in seconds after speech ends.

How the modes behave

DEFAULT: Fixed wait within your min–max range. For clear utterances you respond near the minimum; for hesitations you wait near the maximum.
ADAPTIVE: The wait scales with confidence. Low confidence (hesitation) increases wait; high confidence shortens it, always clamped to your min–max.

What’s Next

VAD and Interruptions

Pair turn detection with Silero VAD.

De-noise

Feed the detector cleaner input audio.

References

Python

Examples

Cascade Basic

Voice agent with a turn detector configured.

SDK Reference

End of Utterance

End of Utterance in the Python API reference.

Get started

Modalities

Configure Pipeline

Tools and Capabilities

Turn Detection and Interruptions

Telephony Agents

Context Management

Observability and Monitoring

Echo Turn Detector

How It Works

Models

Supported Languages

Usage

Performance

Choosing a Model

End-of-Utterance Handling

How the modes behave

What’s Next

VAD and Interruptions

De-noise

References

Examples

Cascade Basic

SDK Reference

End of Utterance

​Echo Turn Detector

​How It Works

​Models

​Supported Languages

​Usage

​Performance

​Choosing a Model

​End-of-Utterance Handling

​How the modes behave

​What’s Next

VAD and Interruptions

De-noise

​References

​Examples

Cascade Basic

​SDK Reference

End of Utterance

Echo Turn Detector

How It Works

Models

Supported Languages

Usage

Performance

Choosing a Model

End-of-Utterance Handling

How the modes behave

What’s Next

References

Examples

SDK Reference