async def api_speech_to_text() -> str:
"""Transcribe speech from WAV file."""
no_header = request.args.get("noheader", "false").lower() == "true"
assert core is not None
# Prefer 16-bit 16Khz mono, but will convert with sox if needed
wav_data = await request.data
if no_header:
# Wrap in WAV
wav_data = buffer_to_wav(wav_data)
start_time = time.perf_counter()
result = await core.transcribe_wav(wav_data)
end_time = time.perf_counter()
if prefers_json():
return jsonify(
{
"text": result.text,
"likelihood": result.confidence,
"transcribe_seconds": (end_time - start_time),
"wav_seconds": get_wav_duration(wav_data),
}
)
return result.text
async def api_speech_to_text() -> str:
"""Transcribe speech from WAV file."""
global last_voice_wav
no_header = request.args.get("noheader", "false").lower() == "true"
assert core is not None
# Prefer 16-bit 16Khz mono, but will convert with sox if needed
wav_data = await request.data
if no_header:
# Wrap in WAV
wav_data = buffer_to_wav(wav_data)
last_voice_wav = wav_data
start_time = time.perf_counter()
result = await core.transcribe_wav(wav_data)
end_time = time.perf_counter()
# Send to websocket
await add_ws_event(
"transcription",
json.dumps({
"text": result.text,
"wakewordId": "default",
"siteId": core.siteId
}),
)
if prefers_json():
return jsonify({
"text": result.text,
"likelihood": result.confidence,
"transcribe_seconds": (end_time - start_time),
"wav_seconds": get_wav_duration(wav_data),
})
return result.text