Barge-in

Barge-in is the ability for a user to interrupt an avatar while it is speaking, so the system can stop the current response, listen to the new input, and continue the conversation naturally.

How barge-in works

Barge-in is the ability for a user to interrupt an avatar while it is speaking. Without barge-in, the user has to wait for the full response to finish, which makes the interaction feel scripted and slow.

Technically, the system has to keep listening while audio is playing, detect that the user has started speaking, stop or fade the avatar's current output, and pass the new user turn into the agent.

A concrete example: an avatar begins explaining pricing, but the buyer says, "Actually, I only need the API limits." Barge-in lets the avatar stop the old answer and switch to the specific question.

Good barge-in is a sign that the system is truly conversational. It depends on fast voice activity detection, careful audio handling and an agent loop that can abandon one response cleanly when the user changes direction.

What Anam ships

Anam's Cara-4 model delivers expressive real-time avatars with around 150 ms server-side avatar-generation latency once a session is running, across 70+ languages. Builders use JavaScript and Python SDKs or integrations for LiveKit, Pipecat, ElevenLabs Agents, Agora, and VideoSDK. Bring any AI stack including OpenAI, Claude, Gemini, Mistral, Groq, Deepgram, Cartesia, or custom providers. The platform supports WebRTC delivery, SOC 2 Type II, HIPAA, zero data retention, and regional data residency. Sessions stream low-latency audio and video to browsers and native apps.

Explore the real-time avatar API →

Related terms

Turn detection

Turn detection is the process of deciding when a user has finished speaking, so the avatar can respond at the right moment without interrupting or waiting too long.

ASR (speech recognition)

ASR, or automatic speech recognition, is the system that converts live spoken audio into text so an avatar or agent can understand the user and decide what to do next.

Interactive avatar

An interactive avatar is a digital character that listens to a user and responds in real time, using speech, language model reasoning, and live animation to support a two-way conversation instead of a fixed script.

Sub-second latency

Sub-second latency is the end-to-end response time under one second between a user speaking and an avatar replying, covering speech recognition, model reasoning, speech synthesis, animation, and network streaming.

Frequently asked questions

Why is barge-in important for avatar conversations?

Barge-in lets users interrupt naturally, just like they would with a person. Without it, the avatar feels like it is delivering a scripted monologue.

What has to happen when a user barges in?

The system needs to detect the user's speech, stop or fade the current avatar output, capture the new turn, and pass it back into the agent loop quickly.

Does barge-in require always-on listening?

During an active session, the system usually needs to monitor microphone input while the avatar speaks. Products should pair this with clear permissions and responsible audio handling.

What makes barge-in feel bad?

It feels bad when the avatar cuts off too easily, ignores the interruption, or takes too long to switch context. Good barge-in needs careful turn detection and fast response handling.

Last updated: 17th July 2026 · Reviewed quarterly.

← Back to glossary