Text-to-Speech Conversion using Sarvam AI API

1
!pip install requests

1
import requests
2
import base64
3
import wave

1
SARVAM_AI_API="d75d7bf3-b053-4084-ac80-c37561a35bfc"

1
# API endpoint and headers
2
url = "https://api.sarvam.ai/text-to-speech"
3
headers = {
4
    "Content-Type": "application/json",
5
    "api-subscription-key": SARVAM_AI_API  # Replace with your valid API key
6
}

1
text = """
2
Netaji Subhash Marg से Dayanand Road की तरफ, south की तरफ़ जाने से शुरू करें। Dayanand Road पर पहुँचने के बाद, बाएँ मुड़ जाएँ। 350 meters तक सीधा चलते रहें।आपको बायें तरफ़, United Bank of India ATM दिखेगा। Dayanand School के दाएँ तरफ़ से गुजरने के बाद, बाएँ मुड़ें।
3
120 meters के बाद, Ghata Masjid Road पर, right turn करें।
4
280 meters तक चलते रहें।
5
Mahatma Gandhi Marg पे रहें और, 2.9 kilometers तक Old Delhi की तरफ जाएँ।
6
फिर, HC Sen Marg पर continue करें, और Paranthe Wali Gali तक drive करें।
7
"""

1
# Split the text into chunks of 500 characters or less
2
chunk_size = 500
3
chunks = [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]
4
5
# Print the number of chunks
6
print(f"Total chunks: {len(chunks)}")

1
# Iterate over each chunk and make the API call
2
for i, chunk in enumerate(chunks):
3
    # Prepare the payload for the API request
4
    payload = {
5
        "inputs": [chunk],
6
        "target_language_code": "kn-IN",  # Target language code (Kannada in this case)
7
        "speaker": "neel",  # Speaker voice
8
        "model": "bulbul:v1",  # Model to use
9
        "pitch": 0,  # Pitch adjustment
10
        "pace": 1.0,  # Speed of speech
11
        "loudness": 1.0,  # Volume adjustment
12
        "enable_preprocessing": True,  # Enable text preprocessing
13
    }
14
15
    # Make the API request
16
    response = requests.post(url, json=payload, headers=headers)
17
    print(response.json())
18
    # Check if the request was successful
19
    if response.status_code == 200:
20
        # Decode the base64-encoded audio data
21
        audio = response.json()["audios"][0]
22
       
23
        audio = base64.b64decode(audio)
24
25
        # Save the audio as a .wav file
26
        with wave.open(f"output{i}.wav", "wb") as wav_file:
27
            # Set the parameters for the .wav file
28
            wav_file.setnchannels(1)  # Mono audio
29
            wav_file.setsampwidth(2)  # 2 bytes per sample
30
            wav_file.setframerate(22050)  # Sample rate of 22050 Hz
31
32
            # Write the audio data to the file
33
            wav_file.writeframes(audio)
34
35
        print(f"Audio file {i} saved successfully as 'output{i}.wav'!")
36
    else:
37
        # Handle errors
38
        print(f"Error for chunk {i}: {response.status_code}")
39
        print(response.json())