undefined

A typical OpenAI voice app on the local sound card: `pip install "ag2[openai-realtime]" "sounddevice[numpy]"`.

> Required. Run the relevant install before delivering code. Without the matching extra, the public symbol resolves to a placeholder that raises `ImportError` (`openai`/`gemini`) or the additional-dependency error (`sounddevice[numpy]`) the moment you use it.

mic ──SoundDeviceRecorder──▶ RecordedAudioEvent ──▶ provider session (Gemini/OpenAI)
                                                       │
                                       SynthesizedAudioEvent (assistant audio)
                                                       ▼
                                              SoundDevicePlayer ──▶ speaker

import asyncio

from ag2.live import (
    LiveAgent,
    OpenAIRealTimeConfig,
    SoundDevicePlayer,
    SoundDeviceRecorder,
)
from ag2.live.openai import AudioOutput, InputConfig

agent = LiveAgent(
    "voice_bot",
    "You are a friendly realtime voice assistant. Keep replies short and conversational.",
    config=OpenAIRealTimeConfig(
        "gpt-realtime",
        output=AudioOutput(voice="marin"),
        # Transcribe the user's speech so we can see it too.
        input=InputConfig(transcription={"model": "gpt-4o-mini-transcribe"}),
    ),
)

async def main() -> None:
    # run() yields the shared ConversationContext.
    async with agent.run() as ctx:
        # Recorder and player bind to the SAME context so audio flows on one bus.
        async with (
            SoundDeviceRecorder(context=ctx),   # mic  -> RecordedAudioEvent
            SoundDevicePlayer(context=ctx),     # SynthesizedAudioEvent -> speaker
        ):
            print("Talk to the agent. Ctrl-C to stop.")
            await asyncio.Event().wait()  # keep the session open

if __name__ == "__main__":
    asyncio.run(main())

from ag2.live import GeminiRealTimeConfig
from ag2.live.gemini import AudioOutput, InputConfig

agent = LiveAgent(
    "voice_bot",
    "You are a friendly realtime voice assistant.",
    config=GeminiRealTimeConfig(
        "gemini-2.5-flash-native-audio-preview-12-2025",
        output=AudioOutput(voice="Kore"),
        input=InputConfig(transcribe=True),   # user-speech transcription
    ),
)

from ag2.live import SoundDeviceRecorder, SoundDevicePlayer

`SoundDeviceRecorder` also has a **one-shot blocking** `record(duration)` that returns a `VoiceInput` (16-bit PCM) — handy to feed the STT pipeline below without running a live session:

```python
voice = recorder.record(duration=4.0)   # blocks 4s, returns VoiceInput  [needs audio]

from ag2 import Agent
from ag2.config import OpenAIConfig
from ag2.live import OpenAITranscriber, SoundDeviceRecorder
from ag2.live.stt import VoiceInput

agent = Agent("assistant", "You answer questions.", config=OpenAIConfig(model="gpt-4o-mini"))
pipeline = OpenAITranscriber("gpt-4o-transcribe").pipe(agent)

`VoiceInput(content: bytes, frame_rate: int, channels: int)` wraps 16-bit PCM; build it directly from any PCM source if you aren't using the recorder.

`OpenAITranslationTranscriber` is identical but always outputs English (useful for non-English speech in → English text out).

from ag2.live import OpenAITTSConfig

tts = OpenAITTSConfig("gpt-4o-mini-tts", voice="alloy", speed=1.0)
pcm: bytes = await tts.synthesize("Hello there!")   # [needs keys]

from ag2 import Agent, MemoryStream
from ag2.config import OpenAIConfig
from ag2.context import ConversationContext
from ag2.live import OpenAITTSConfig, SoundDevicePlayer, TTSObserver

agent = Agent(
    "narrator",
    "You are a helpful assistant.",
    config=OpenAIConfig(model="gpt-4o-mini"),
    observers=[TTSObserver(OpenAITTSConfig("gpt-4o-mini-tts", voice="nova"))],
)

`TTSObserver(config)` returns a `CompositeObserver`. It flushes any remaining buffered text on the final `ModelMessage`, so trailing partial sentences are still spoken.