Speaker diarization API for real-time and recorded audio

{
  "model": "stt-rt-v5",
  "enable_speaker_diarization": true
}

{"text": "How",    "speaker": "1"}
{"text": " are",   "speaker": "1"}
{"text": " you",   "speaker": "1"}
{"text": "?",      "speaker": "1"}
{"text": "I",      "speaker": "2"}
{"text": " am",    "speaker": "2"}
{"text": " fan",   "speaker": "2"}
{"text": "tastic", "speaker": "2"}

from soniox import SonioxClient
from soniox.types import RealtimeSTTConfig
from soniox.utils import start_audio_thread, throttle_audio

client = SonioxClient()
config = RealtimeSTTConfig(
    model="stt-rt-v5",
    audio_format="mp3",
    enable_speaker_diarization=True,
)

audio = throttle_audio("meeting.mp3", delay_seconds=0.1)

with client.realtime.stt.connect(config=config) as session:
    start_audio_thread(session, audio)

    current_speaker = None
    for event in session.receive_events():
        for token in event.tokens:
            if not token.is_final:
                continue
            if token.speaker != current_speaker:
                current_speaker = token.speaker
                print(f"\nSpeaker {current_speaker}:", end="")
            print(token.text, end="", flush=True)