Getting started

Deployments:SaaSStatus:Early Access

Flow is our Conversational AI API that allows you to add responsive, real-time speech-to-speech interactions to any product.

Flow is engineered to engage in natural and fluid conversations by automatically handling interruptions, responding to multiple speakers, and understanding different dialects and accents.

The easiest way to get started is by downloading the Speechmatics Flow iOS app.

This page will show you how to use the Flow Conversational API for the most natural and intuitive conversational AI using an easy to use interactive code editor.

Set Up

1. Create an account on the Speechmatics On-Demand Portal here.
2. Navigate to Manage > API Keys page in the Speechmatics On-Demand Portal.
3. Enter a name for your API key and store your API key somewhere safe.

Code Examples

CLI

The Speechmatics Flow library and CLI can found on GitHub and installed using pip:

pip3 install speechmatics-flow

Speak with Flow directly from your terminal. Just copy in your API key to get started!

flow --url wss://flow.api.speechmatics.com/v1/flow --ssl-mode insecure --auth-token $API_KEY -

Python

The Speechmatics Flow library and CLI can found on GitHub and installed using pip:

pip3 install speechmatics-flow

Speak with Flow with this Python code example. Just copy in your API key and file name to get started!

1import asyncio
2import io
3import ssl
4import sys
5
6import pyaudio
7
8from speechmatics_flow.client import WebsocketClient
9from speechmatics_flow.models import (
10    ConnectionSettings,
11    Interaction,
12    AudioSettings,
13    ConversationConfig,
14    ServerMessageType,
15)
16
17AUTH_TOKEN = "Place your auth token here"
18
19
20ssl_context = ssl.create_default_context()
21ssl_context.check_hostname = False
22ssl_context.verify_mode = ssl.CERT_NONE
23# Create a websocket client
24client = WebsocketClient(
25    ConnectionSettings(
26        url="wss://flow.api.speechmatics.com/v1/flow",
27        auth_token=AUTH_TOKEN,
28        ssl_context=ssl_context,
29    )
30)
31
32# Create a buffer to store binary messages sent from the server
33audio_buffer = io.BytesIO()
34
35
36# Create callback function which adds binary messages to audio buffer
37def binary_msg_handler(msg: bytes):
38    if isinstance(msg, (bytes, bytearray)):
39        audio_buffer.write(msg)
40
41
42# Register the callback which will be called
43# when the client receives an audio message from the server
44client.add_event_handler(ServerMessageType.audio, binary_msg_handler)
45
46
47async def audio_playback(buffer):
48    """Read from buffer and play audio back to the user"""
49    p = pyaudio.PyAudio()
50    stream = p.open(format=pyaudio.paInt16, channels=1, rate=16000, output=True)
51    try:
52        while True:
53            # Get the current value from the buffer
54            audio_to_play = buffer.getvalue()
55            # Only proceed if there is audio data to play
56            if audio_to_play:
57                # Write the audio to the stream
58                stream.write(audio_to_play)
59                buffer.seek(0)
60                buffer.truncate(0)
61            # Pause briefly before checking the buffer again
62            await asyncio.sleep(0.05)
63    finally:
64        stream.close()
65        stream.stop_stream()
66        p.terminate()
67
68
69async def main():
70    tasks = [
71        # Use the websocket to connect to Flow Service and start a conversation
72        asyncio.create_task(
73            client.run(
74                interactions=[Interaction(sys.stdin.buffer)],
75                audio_settings=AudioSettings(),
76                conversation_config=ConversationConfig(),
77            )
78        ),
79        # Run audio playback handler which streams audio from audio buffer
80        asyncio.create_task(audio_playback(audio_buffer)),
81    ]
82
83    await asyncio.gather(*tasks)
84
85
86asyncio.run(main())
87

JavaScript

The easiest way to get started in a browser context is with this JS Fiddle, simply copy in your API key and press START!

You can also get started locally with this equivalent Vanilla JS example.