Using Microphone Input
The example below will help you transcribe your voice by using the official Speechmatics Python library and CLI.
You can of course integrate with Speechmatics using our Official JavaScript SDK, or in the programming language of your choice by referring to the Real-Time API Reference.
Setup
The Speechmatics Python library and CLI can be installed using pip:
pip3 install speechmatics-python
Transcribe your voice in real-time using the Speechmatics Python library. Just copy in your API key to get started!
In order to use this script, you may also need to install PyAudio by running:
pip3 install pyaudio
brew install portaudio
brew link portaudio
BREW_PREFIX=$(brew --prefix)
CFLAGS="-I$BREW_PREFIX/include -L$BREW_PREFIX/lib" python3 -m pip install pyaudio
Code Example
1import speechmatics
2from httpx import HTTPStatusError
3import asyncio
4import pyaudio
5
6API_KEY = "YOUR_API_KEY"
7LANGUAGE = "en"
8CONNECTION_URL = f"wss://eu2.rt.speechmatics.com/v2/{LANGUAGE}"
9DEVICE_INDEX = -1
10CHUNK_SIZE = 1024
11
12
13class AudioProcessor:
14 def __init__(self):
15 self.wave_data = bytearray()
16 self.read_offset = 0
17
18 async def read(self, chunk_size):
19 while self.read_offset + chunk_size > len(self.wave_data):
20 await asyncio.sleep(0.001)
21 new_offset = self.read_offset + chunk_size
22 data = self.wave_data[self.read_offset:new_offset]
23 self.read_offset = new_offset
24 return data
25
26 def write_audio(self, data):
27 self.wave_data.extend(data)
28 return
29
30
31audio_processor = AudioProcessor()
32# PyAudio callback
33def stream_callback(in_data, frame_count, time_info, status):
34 audio_processor.write_audio(in_data)
35 return in_data, pyaudio.paContinue
36
37# Set up PyAudio
38p = pyaudio.PyAudio()
39if DEVICE_INDEX == -1:
40 DEVICE_INDEX = p.get_default_input_device_info()['index']
41 device_name = p.get_default_input_device_info()['name']
42 DEF_SAMPLE_RATE = int(p.get_device_info_by_index(DEVICE_INDEX)['defaultSampleRate'])
43 print(f"***\nIf you want to use a different microphone, update DEVICE_INDEX at the start of the code to one of the following:")
44 # Filter out duplicates that are reported on some systems
45 device_seen = set()
46 for i in range(p.get_device_count()):
47 if p.get_device_info_by_index(i)['name'] not in device_seen:
48 device_seen.add(p.get_device_info_by_index(i)['name'])
49 try:
50 supports_input = p.is_format_supported(DEF_SAMPLE_RATE, input_device=i, input_channels=1, input_format=pyaudio.paFloat32)
51 except Exception:
52 supports_input = False
53 if supports_input:
54 print(f"-- To use << {p.get_device_info_by_index(i)['name']} >>, set DEVICE_INDEX to {i}")
55 print("***\n")
56
57SAMPLE_RATE = int(p.get_device_info_by_index(DEVICE_INDEX)['defaultSampleRate'])
58device_name = p.get_device_info_by_index(DEVICE_INDEX)['name']
59
60print(f"\nUsing << {device_name} >> which is DEVICE_INDEX {DEVICE_INDEX}")
61print("Starting transcription (type Ctrl-C to stop):")
62
63stream = p.open(format=pyaudio.paFloat32,
64 channels=1,
65 rate=SAMPLE_RATE,
66 input=True,
67 frames_per_buffer=CHUNK_SIZE,
68 input_device_index=DEVICE_INDEX,
69 stream_callback=stream_callback
70)
71
72# Define connection parameters
73conn = speechmatics.models.ConnectionSettings(
74 url=CONNECTION_URL,
75 auth_token=API_KEY,
76)
77
78# Create a transcription client
79ws = speechmatics.client.WebsocketClient(conn)
80
81# Define transcription parameters
82# Full list of parameters described here: https://speechmatics.github.io/speechmatics-python/models
83conf = speechmatics.models.TranscriptionConfig(
84 operating_point="enhanced",
85 language=LANGUAGE,
86 enable_partials=True,
87 max_delay=1,
88)
89
90# Define an event handler to print the partial transcript
91def print_partial_transcript(msg):
92 print(f"[partial] {msg['metadata']['transcript']}")
93
94# Define an event handler to print the full transcript
95def print_transcript(msg):
96 print(f"[ FINAL] {msg['metadata']['transcript']}")
97
98# Register the event handler for partial transcript
99ws.add_event_handler(
100 event_name=speechmatics.models.ServerMessageType.AddPartialTranscript,
101 event_handler=print_partial_transcript,
102)
103
104# Register the event handler for full transcript
105ws.add_event_handler(
106 event_name=speechmatics.models.ServerMessageType.AddTranscript,
107 event_handler=print_transcript,
108)
109
110settings = speechmatics.models.AudioSettings()
111settings.encoding = "pcm_f32le"
112settings.sample_rate = SAMPLE_RATE
113settings.chunk_size = CHUNK_SIZE
114
115print("Starting transcription (type Ctrl-C to stop):")
116try:
117 ws.run_synchronously(audio_processor, conf, settings)
118except KeyboardInterrupt:
119 print("\nTranscription stopped.")
120except HTTPStatusError as e:
121 if e.response.status_code == 401:
122 print('Invalid API key - Check your API_KEY at the top of the code!')
123 else:
124 raise e
125
126
Enhanced Voice AI Features
For building voice AI applications, translation systems, or dictation software with microphone input, consider enabling End of Utterance Detection. This feature detects when users finish speaking by monitoring silence periods, enabling natural turn-taking and responsive voice applications.
The end-of-utterance feature works perfectly with microphone streaming and can be added to the configuration above by including conversation_config
with a silence threshold parameter.