This guide walks you through setting up and running a basic audio transcription app using the Spitch Python SDK and Streamlit.

​
Overview

This app allows users to upload audio files (WAV, OGG, M4A or MP3), select a language, and receive an accurate transcription using the Spitch ASR API.

​
🔧 Prerequisites

Before you start, make sure you have:
  • Python 3.7+
  • Streamlit
  • Spitch Python SDK
  • A Spitch API key

​
🚀 Installation

Install the required packages: 
pip install streamlit spitch

​
🧠 App Structure

Your main application code lives in a single file. Here’s a breakdown of its structure:

​
1. Import Modules

import streamlit as st
from spitch import Spitch
import os
import tempfile

​
2. Transcription Logic

def transcribe_audio(audio_file, lang):
    os.environ["SPITCH_API_KEY"] = "YOUR-API-KEY"
    client = Spitch()

    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_file:
        temp_file.write(audio_file.read())
        temp_path = temp_file.name

    with open(temp_path, "rb") as f:
        response = client.speech.transcribe(language=lang, content=f.read())

    return response.text

​
3. Streamlit UI

def main():
    st.title("My Spitch Transcription App")
    st.write("Upload an audio file to transcribe it to text.")

    audio_file = st.file_uploader("Upload Audio", type=["wav", "mp3"])

    if audio_file:
        st.audio(audio_file, format='audio/wav')
        language = st.selectbox("Language", ["English", "Yoruba", "Igbo", "Hausa"])
        lang = {'English': 'en', 'Yoruba': 'yo', 'Igbo': 'ig'}.get(language, 'ha')

        if st.button("Transcribe"):
            with st.spinner("Transcribing..."):
                transcript = transcribe_audio(audio_file, lang)
                st.success("Transcription completed!")
                st.text_area("Transcript", transcript, height=200)
                st.download_button("Download Transcript", data=transcript, file_name="transcript.txt")

if __name__ == "__main__":
    main()

​
🧑‍💻 Access the code here

$ git clone https://github.com/Nalito/My-Spitch-Transcription-App.git
$ cd My-Spitch-Transcription-App

​
🧪 Testing the App

Run the Streamlit app: 
streamlit run app.py
Upload an audio file, select the language, and click Transcribe to test the transcription.

​
🛠️ Make it your own!

Play around with the code to store transcripts in databases, or even integrate with frontend frameworks for a richer UI!