​
Install Dependencies

pip install pyaudio 
pip install reverie-sdk
pip install python-dotenv

​
How does it Works?

The main steps involved in the script are as follows:

  1. Environment Configuration:
    The script loads API credentials (REVERIE_APP_ID and REVERIE_API_KEY) from environment variables using the dotenv package. These credentials are essential for interacting with the Reverie SDK’s ASR (Automatic Speech Recognition) service.
Python
import os
import dotenv
from reverie_sdk import ReverieClient

dotenv.load_dotenv("../.env")
REVERIE_APP_ID = os.environ.get("REVERIE_APP_ID")
REVERIE_API_KEY = os.environ.get("REVERIE_API_KEY")
client = ReverieClient(
    api_key=REVERIE_API_KEY,
    app_id=REVERIE_APP_ID,
)
  1. Real-Time Audio Capture:
    The script uses the pyaudio library to stream audio from the user’s microphone in real-time. The audio is captured in 16kHz, mono format (16-bit signed integer), and streamed asynchronously to Reverie’s ASR service for transcription.
Python
import pyaudio
import asyncio

stream = AudioStream()
pa = pyaudio.PyAudio()

def mic_callback(in_data, frame_count, time_info, status):
    try:
        asyncio.run(stream.add_chunk_async(in_data))
    except Exception as e:
        print(f"Error in mic callback: {e}")
        return (None, pyaudio.paAbort)
    return (None, pyaudio.paContinue)

pa_stream = pa.open(
    rate=16000,
    channels=1,
    format=pyaudio.paInt16,
    frames_per_buffer=1024,
    input=True,
    stream_callback=mic_callback,
)
pa_stream.start_stream()
  1. Speech-to-Text (STT) Conversion:
    The captured audio is sent in small chunks to the Reverie ASR system, which transcribes the speech into text. The transcription is processed as it is received, with results updated in real-time.
Python
from reverie_sdk.services.asr import ReverieAsrResult, AudioStream

await client.asr.stt_stream_async(
    src_lang=source_lang,
    bytes_or_stream=stream,
    callback=asr_callback,
    format="16k_int16",
    punctuate="true",
)
  1. Asynchronous Processing:
    An asynchronous function handles the audio streaming and transcription. A callback function is used to manage the incoming transcription results, which are accumulated and processed until a final transcription result is achieved.
Python
async def speech_to_text(source_lang):
    asr_responses: list[ReverieAsrResult] = []

    def asr_callback(resp: ReverieAsrResult):
        print(resp)
        asr_responses.append(resp)

    while True:
        if len(asr_responses) == 0:
            continue

        if asr_responses[-1].final:
            print(asr_responses[-1].display_text)
            return asr_responses[-1].display_text
  1. Error Handling:
    The script includes robust error handling to manage any issues that may arise during the microphone input, audio streaming, or ASR transcription process.
Python
import traceback

try:
    # [Audio streaming and transcription code]
except Exception as err:
    print(f"Error in Speech-to-Text: {err}")
    traceback.print_exc()
finally:
    pa_stream.stop_stream()
    pa_stream.close()
  1. Output:
    Once the transcription is complete, the final text is printed out. The transcription happens in the source language (Hindi in this example), and it’s ready for further processing or translation if needed.

​
Sample Code

import asyncio
import os
import traceback
import pyaudio
from reverie_sdk import ReverieClient
from reverie_sdk.services.asr import ReverieAsrResult, AudioStream
import dotenv

dotenv.load_dotenv("../.env")

REVERIE_APP_ID = os.environ.get("REVERIE_APP_ID")
REVERIE_API_KEY = os.environ.get("REVERIE_API_KEY")

client = ReverieClient(
    api_key=REVERIE_API_KEY,
    app_id=REVERIE_APP_ID,
)


async def speech_to_text(source_lang):
    stream = AudioStream()
    pa = pyaudio.PyAudio()

    def mic_callback(in_data, frame_count, time_info, status):
        try:
            asyncio.run(stream.add_chunk_async(in_data))
        except Exception as e:
            print(f"Error in mic callback: {e}")
            return (None, pyaudio.paAbort)
        return (None, pyaudio.paContinue)

    pa_stream = pa.open(
        rate=16000,
        channels=1,
        format=pyaudio.paInt16,
        frames_per_buffer=1024,
        input=True,
        stream_callback=mic_callback,
    )
    pa_stream.start_stream()

    print("Listening at STT..")

    asr_responses: list[ReverieAsrResult] = []

    def asr_callback(resp: ReverieAsrResult):
        print(resp)
        asr_responses.append(resp)

    try:
        await client.asr.stt_stream_async(
            src_lang=source_lang,
            bytes_or_stream=stream,
            callback=asr_callback,
            format="16k_int16",
            punctuate="true",
        )

        while True:
            if len(asr_responses) == 0:
                continue

            if asr_responses[-1].final:
                print(asr_responses[-1].display_text)
                return asr_responses[-1].display_text

    except Exception as err:
        print(f"Error in Speech-to-Text: {err}")
        traceback.print_exc()

    finally:
        pa_stream.stop_stream()
        pa_stream.close()


asyncio.run(speech_to_text("hi"))