Voice Adapter Capability Matrix

Every voice adapter in Scenario declares its capabilities via a frozen AdapterCapabilities record (Python capabilities.py, TypeScript voice.AdapterCapabilities). The Python table is auto-generated from those declarations and kept in sync by a CI gate — if you change an adapter's capabilities, regenerate with:

cd python
uv run python scripts/gen_capability_matrix.py

The TypeScript SDK ships a subset of adapters (see javascript/docs/voice/capability-matrix.md for the authoritative TS render).

Capabilities

Adapter	streaming_transcripts	native_vad	dtmf	interruption	input_formats	output_formats
ComposableVoice	✅	❌	❌	❌	`pcm16/24000`	`pcm16/24000`
ElevenLabs	✅	✅	❌	❌	`pcm16/24000`	`pcm16/24000`
GeminiLive	✅	✅	❌	✅	`pcm16/16000`	`pcm16/24000`
LiveKit	✅	✅	❌	❌	`pcm16/48000`	`pcm16/48000`
OpenAIRealtime	✅	✅	❌	✅	`pcm16/24000`	`pcm16/24000`
Pipecat	✅	✅	❌	✅	`pcm16/24000`, `mulaw/8000`, `opus`	`pcm16/24000`, `mulaw/8000`, `opus`
Twilio	❌	❌	✅	✅	`mulaw/8000`	`mulaw/8000`
Vapi	✅	✅	❌	❌	`pcm16/16000`	`pcm16/16000`
WebRTC	❌	❌	❌	❌	`pcm16/24000`	`pcm16/24000`
WebSocket	❌	❌	❌	❌	`pcm16/24000`	`pcm16/24000`

Column key

Column	Meaning
`streaming_transcripts`	Adapter emits incremental transcript events during a turn
`native_vad`	Adapter has built-in voice activity detection
`dtmf`	Adapter can detect and forward DTMF (keypad) tones
`interruption`	Adapter supports barge-in / user-initiated interruption
`input_formats`	Audio formats the adapter accepts from the user simulator
`output_formats`	Audio formats the adapter sends to the scenario harness

Wire transport and shipping status

The capabilities table above describes what each adapter supports. The table below describes how each adapter is wired and whether it is shipping or still stubbed behind PendingTransportError.

TypeScript readers: class names in this table match the Python SDK. TypeScript exports factory functions instead — pipecatAgent, twilioAgent, openAIRealtimeAgent, elevenLabsAgent, geminiLiveAgent, composableAgent. Python-only adapters are noted in the Not yet ported to TypeScript section below.

Adapter	Wire transport	Real I/O?
`ComposableVoiceAgent`	STT + LLM + TTS pipeline (provider-defined)	✅ shipping
`ElevenLabsAgentAdapter`	WebSocket (ElevenLabs Convai)	✅ shipping
`GeminiLiveAgentAdapter`	WebSocket (Gemini Live)	✅ shipping
`LiveKitAgentAdapter`	WebRTC (LiveKit room)	🚧 stub (`PendingTransportError`)
`OpenAIRealtimeAgentAdapter`	WebSocket (OpenAI Realtime)	✅ shipping
`PipecatAgentAdapter`	WebSocket (Twilio Media Streams protocol)	✅ shipping
`TwilioAgentAdapter`	Media Streams (WebSocket over Twilio)	✅ shipping
`VapiAgentAdapter`	REST (Vapi outbound)	🚧 stub (`PendingTransportError`)
`WebRTCAgentAdapter`	WebRTC (datachannel + audio track)	🚧 stub (`PendingTransportError`)
`WebSocketAgentAdapter`	WebSocket (bring-your-own protocol)	✅ shipping

Adapters marked 🚧 raise PendingTransportError on connect() and are tracked as follow-up issues. Their capability declarations are final (they match the wire spec); only the transport glue code is pending.

Not yet ported to TypeScript

These adapters exist in the Python SDK but are not exported from @langwatch/scenario today — do not try to import them in TypeScript (tracked in #563):

Adapter	Status in TypeScript
`LiveKitAgentAdapter`	not ported (Python-only)
`VapiAgentAdapter`	not ported (Python-only)
`WebRTCAgentAdapter` (generic)	not ported (Python-only)
`WebSocketAgentAdapter` (generic)	not ported — subclass `voice.VoiceAgentAdapter` for a custom protocol

Pending transport in TypeScript: WebRTC mode on Pipecat (scenario.pipecatAgent({ transport: "webrtc", signalingUrl })) constructs fine but raises voice.PendingTransportError at connect() until the SmallWebRTC transport lands.

Source of truth

Capability values live in each adapter's capabilities declaration.

Python: capabilities: ClassVar[AdapterCapabilities] per adapter. Canonical source python/scenario/voice/capabilities.py; generator python/scripts/gen_capability_matrix.py.
TypeScript: capabilities: voice.AdapterCapabilities per adapter, read from javascript/src/voice/adapters/*.ts; authoritative render in javascript/docs/voice/capability-matrix.md.