async def mic2wav(core: RhasspyCore, profile: Profile, args: Any) -> None:
"""Record voice command from microphone"""
# Listen until silence
wav_data = buffer_to_wav((await core.record_command(args.timeout)).data)
# Output WAV data
sys.stdout.buffer.write(wav_data)
def api_stop_recording() -> Response:
"""End recording voice command. Transcribe and handle."""
assert core is not None
no_hass = request.args.get("nohass", "false").lower() == "true"
buffer_name = request.args.get("name", "")
audio_data = core.stop_recording_wav(buffer_name).data
wav_data = buffer_to_wav(audio_data)
logger.debug("Recorded %s byte(s) of audio data" % len(wav_data))
transcription = core.transcribe_wav(wav_data)
text = transcription.text
logger.debug(text)
intent = core.recognize_intent(text).intent
intent["speech_confidence"] = transcription.confidence
intent_json = json.dumps(intent)
logger.debug(intent_json)
add_ws_event(WS_EVENT_INTENT, intent_json)
if not no_hass:
# Send intent to Home Assistant
intent = core.handle_intent(intent).intent
return jsonify(intent)
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
def in_started(self, message: Any, sender: RhasspyActor) -> None:
"""Handle messages in started state."""
global last_voice_wav
if isinstance(message, IntentRecognized):
# Add slots
intent_slots = {}
for ev in message.intent.get("entities", []):
intent_slots[ev["entity"]] = ev["value"]
message.intent["slots"] = intent_slots
# Convert to JSON
intent_json = json.dumps(message.intent)
self._logger.debug(intent_json)
asyncio.run_coroutine_threadsafe(add_ws_event("intent", intent_json), loop)
elif isinstance(message, WakeWordDetected):
assert core is not None
wake_json = json.dumps({"wakewordId": message.name, "siteId": core.siteId})
asyncio.run_coroutine_threadsafe(add_ws_event("wake", wake_json), loop)
elif isinstance(message, WavTranscription):
assert core is not None
transcription_json = json.dumps(
{
"text": message.text,
"wakewordId": message.wakewordId,
"siteId": core.siteId,
}
)
asyncio.run_coroutine_threadsafe(
add_ws_event("transcription_json", transcription_json), loop
)
elif isinstance(message, VoiceCommand):
# Save last voice command
last_voice_wav = buffer_to_wav(message.data)
async def mic2text(core: RhasspyCore, profile: Profile, args: Any) -> None:
# Listen until silence
wav_data = buffer_to_wav((await core.record_command(args.timeout)).data)
# Transcribe
text = (await core.transcribe_wav(wav_data)).text
# Output text
print(text)
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)
result = await core.transcribe_wav(wav_data)
return result.text
def in_awake(self, message: Any, sender: RhasspyActor) -> None:
"""Handle messages in awake state."""
if isinstance(message, VoiceCommand):
# Recorded beep
wav_path = os.path.expandvars(self.profile.get("sounds.recorded", None))
if wav_path is not None:
self.send(self.player, PlayWavFile(wav_path))
# speech -> text
wav_data = buffer_to_wav(message.data)
self.send(self.decoder, TranscribeWav(wav_data, handle=message.handle))
self.transition("decoding")
else:
self.handle_any(message, sender)
async def mic2intent(core: RhasspyCore, profile: Profile, args: Any) -> None:
# Listen until silence
wav_data = buffer_to_wav((await core.record_command(args.timeout)).data)
# Transcribe
sentence = (await core.transcribe_wav(wav_data)).text
# Parse
intent = (await core.recognize_intent(sentence)).intent
if args.handle:
intent = (await core.handle_intent(intent)).intent
# Output JSON
json.dump(intent, sys.stdout, indent=4)
async def api_stop_recording() -> Response:
"""End recording voice command. Transcribe and handle."""
global last_voice_wav
assert core is not None
no_hass = request.args.get("nohass", "false").lower() == "true"
buffer_name = request.args.get("name", "")
audio_data = (await core.stop_recording_wav(buffer_name)).data
wav_data = buffer_to_wav(audio_data)
logger.debug("Recorded %s byte(s) of audio data", len(wav_data))
transcription = await core.transcribe_wav(wav_data)
text = transcription.text
logger.debug(text)
# Send to websocket
await add_ws_event(
"transcription",
json.dumps({
"text": text,
"wakewordId": "default",
"siteId": core.siteId
}),
)
intent = (await core.recognize_intent(text)).intent
intent["speech_confidence"] = transcription.confidence
intent_json = json.dumps(intent)
logger.debug(intent_json)
await add_ws_event("intent", intent_json)
if not no_hass:
# Send intent to Home Assistant
intent = (await core.handle_intent(intent)).intent
# Save last voice command WAV data
last_voice_wav = wav_data
return jsonify(intent)
def api_stop_recording() -> Response:
'''End recording voice command. Transcribe and handle.'''
assert core is not None
no_hass = request.args.get('nohass', 'false').lower() == 'true'
buffer_name = request.args.get('name', '')
audio_data = core.stop_recording_wav(buffer_name).data
wav_data = buffer_to_wav(audio_data)
logger.debug('Recorded %s byte(s) of audio data' % len(wav_data))
text = core.transcribe_wav(wav_data).text
logger.debug(text)
intent = core.recognize_intent(text).intent
logger.debug(intent)
if not no_hass:
# Send intent to Home Assistant
intent = core.handle_intent(intent).intent
return jsonify(intent)
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
