Piper TTS
Piper TTS is a generative audio model for text-to-speech generation
Deploy Piper TTS behind an API endpoint in seconds.
Deploy modelExample usage
Piper TTS is a generative audio model for text-to-speech generation. This model can be trained on various voices to create realistic output audio. This model has very low latency and is optimized to run on a Raspberry Pi!
1import base64
2import requests
3import os
4
5# Paste model id below
6model_id = ""
7baseten_api_key = os.environ["BASETEN_API_KEY"]
8
9def base64_to_wav(base64_string, output_file_path):
10 binary_data = base64.b64decode(base64_string)
11 with open(output_file_path, "wb") as wav_file:
12 wav_file.write(binary_data)
13
14text = "Listen up, people. Life's a wild ride, and sometimes you gotta grab it by the horns and steer it where you want to go. You can't just sit around waiting for things to happen – you gotta make 'em happen. Yeah, it's gonna get tough, but that's when you dig deep, find that inner badass, and come out swinging. Remember, success ain't handed to you on a silver platter; you gotta snatch it like it owes you money. So, lace up your boots, square those shoulders, and let the world know that you're here to play, and you're playing for keeps"
15data = {"text": text}
16
17res = requests.post(
18 f"https://model-{model_id}.api.baseten.co/production/predict",
19 headers={"Authorization": f"Api-Key {baseten_api_key}"},
20 json=data
21)
22res = res.json()
23
24output = base64_to_wav(res.get('output'), "piper-tts-output.wav")
25os.system("open piper-tts-output.wav")
1{
2 "output": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQACAIAAA..."
3}