Live Transcription

import os, asyncio
from fennec_asr import Realtime
from fennec_asr.mic import stream_microphone

API_KEY = "YOUR_API_KEY"
SAMPLE_RATE = 16000
CHANNELS = 1
CHUNK_MS = 32
SINGLE_UTTERANCE = False
DETECT_THOUGHTS = False

# Note: This is a very aggressive VAD setting for high speed transcription.
VAD = {
    "threshold": 0.5,  # VAD sensitivity. Lower is more sensitive. 0.5 is a good baseline.
    "min_silence_ms": 100,  # Milliseconds of silence to trigger an End-of-Speech event.
    "speech_pad_ms": 200,  # Milliseconds of audio to include before speech starts.
    "final_silence_s": 0.1, # Additional silence to wait for at the end.
    "start_trigger_ms": 36,  # How many ms of speech are needed to start transcribing.
    "min_voiced_ms": 48,  # Utterance is discarded if it has less than this much voiced audio.
    "min_chars": 1,  # Discard transcript if it has fewer characters than this.
    "min_words": 1,  # Discard transcript if it has fewer words than this.
    "amp_extend": 1200,  # A non-speech noise can extend utterance, but not start it.
    "force_decode_ms": 0,  # Forces a transcription after a set amount of ms have elapsed
    "debug": False,   # show debugging messages
}

async def main():
    if not API_KEY:
        raise RuntimeError("Set FENNEC_API_KEY")

    rt = (
        Realtime(API_KEY, sample_rate=SAMPLE_RATE, channels=CHANNELS, detect_thoughts=DETECT_THOUGHTS)
        .on("open",  lambda: print("✅ ready"))
        .on("final", lambda t: print("📝", t))
        .on("error", lambda e: print("❌", e))
    )

    rt._start_msg["single_utterance"] = SINGLE_UTTERANCE
    rt._start_msg["vad"] = VAD

    async with rt:
        await stream_microphone(rt, samplerate=SAMPLE_RATE, channels=CHANNELS, chunk_ms=CHUNK_MS)

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