LiveKit voice integration for Mastra agents — realtime voice with semantic turn detection and barge-in

Barge-in coordinator: watches inbound audio via vad-engine, fires interrupt() on adapter when user speaks during agent playback (Section 24 VOICE)

Browser/edge client for dmstfy-voice-core: typed events, WebSocket transport, barge-in aware voice sessions

Browser SDK for OmniDimension web call Sessions: microphone capture, audio playback, barge-in, transcripts.

Official JavaScript/TypeScript SDK for the VSIP Voice Events API — real-time turn detection, identity-gated barge-in, and speaker verification for voice agents.

Bidirectional voice for a composer — open mic, live transcript, spoken replies, barge-in. One machine and one button, shared by hanzo.chat and hanzo.app.

Official TypeScript SDK for sipgate flow — the GDPR-compliant, EU-hosted real-time voice and telephony layer for AI phone agents. Connect phone calls to your own AI agents (speech-to-text, text-to-speech, instant barge-in).

Bridge Microsoft Teams voice/video calls to an ElevenLabs Agent. Terminates the StandIn media bridge wire protocol on one side and the ElevenLabs Agent WebSocket on the other. No transcoding: PCM 16k verbatim both ways, barge-in, on-demand vision, call go

One-line bridge from a Twilio Media Streams phone call to a PyAI Omni voice agent, handles mu-law/PCM16 transcode, resampling, barge-in, DTMF, and engine-native call control (transfer, hangup) for you.

Silero VAD barge-in plugin for ArionTalk — AI-powered voice activity detection

Put an OpenAI Realtime voice agent on Microsoft Teams calls. Terminates the StandIn media bridge wire protocol on one side and the OpenAI Realtime API WebSocket on the other: barge-in, function tools, on-demand vision, call governors. PCM 16k on the wire,

Echo VoiceFlow client with client-side VAD, turn control (push-to-talk / auto / hybrid), local barge-in, waveform and mute. Vanilla core + React hook.

Native voice streaming Expo module — Android AAR + iOS xcframework coordinator (capture, playback, AEC/AGC, barge-in, waiting sound, telemetry).

Telenow voice AI SDK for the browser — add real-time AI voice agent calls to any web app: mic capture, echo & noise suppression, adaptive jitter buffer, barge-in, auto-reconnect, live transcripts. WebSocket or WebRTC transport (chosen by the agent, transp

Gen's speech system. ElevenLabs streaming, AudioWorklet lip sync, barge-in detection.

OpenClaw realtime-voice provider bridging gateway-relay to an external Pipecat speech-to-speech server (on-device Voxtral STT + LLM + TTS with heard-grounded barge-in).

Twilio Media Streams WebSocket handler for voice AI agents with barge-in detection and full call lifecycle management

Headless browser primitives for voice conversations with Pikku AI agents — persistent microphone, silence detection, speech playback and barge-in

Put a Cartesia Line voice agent on Microsoft Teams calls. Terminates the StandIn media bridge wire protocol on one side and the Cartesia Line agent WebSocket on the other. No transcoding: the base64 PCM 16k payload is relayed verbatim both ways, barge-in

Put a Deepgram Voice Agent on Microsoft Teams calls. Terminates the StandIn media bridge wire protocol on one side and the Deepgram Voice Agent WebSocket on the other. No transcoding: PCM 16k verbatim both ways, barge-in, extensible client-side tools, vis