🗣️ (Alpha) iApp Text-to-Speech (TTS) + Voice Cloning 🆕

🗣️ AI-powered text-to-speech synthesis API

Welcome to iApp TTSv3 API, a cutting-edge text-to-speech synthesis service that converts text into natural-sounding speech. Our API uses an advanced AI model to generate audio from text input with excellent accuracy and speed.

Try Demo

Example File (Click to try)

Selected: vc-demo.mp3

API Key

Demo key is limited to 10 requests per day per IP
Click here to get your API key

Endpoint URL

cURL Command

Please input the text you want to translate here.

Please input your Source Voice Text

Upload Audio File

Getting Started

Prerequisites

• Text input in English only
• Maximum tokens: 1400
• Output format: WAV
• Source voice file: WAV format (Optional)

Quick Start

• Fast processing with GPU acceleration
• Natural speech generation
• High-quality speech output

Key Features

• Voice clone from source voice file
• Text input in English only
• Natural speech synthesis using state-of-the-art AI
• Advanced voice quality tuning via parameters
• High-speed response times
• Simple REST API interface

API Usage

Endpoints

• POST /tts - Generate speech from text and download as a file

API Request Examples

Using cURL with source voice file to clone voice:

# Health check
curl http://localhost:8000/health

# Generate speech and save to file
curl -X POST http://localhost:8000/tts \
  -H "Content-Type: multipart/form-data" \
  -F "text=Hello, this is a test." \
  -F "source_vc_text=Transcription of source_voice_clone.wav file" \
  -F "temperature=0.7" \
  -F "top_p=0.95" \
  -F "source_voice_file=@source_voice_clone.wav" \
  --output test.wav

Using Python with source voice file to clone voice:

import requests
with open("source_voice_clone.wav", "rb") as f:
    # Text-to-speech request
    response = requests.post(
        "http://localhost:8000/tts",
        files={
            "source_vc_file": ("source_voice_clone.wav", f, "audio/wav")
        },
        data={
        "text": "Hello, this is a test.",
        "temperature": 0.9,
        "top_p": 0.95,
        "max_new_tokens": 1400,
        "source_vc_text": "Transcription of source_voice_clone.wav file"
        }
    )

# Save the audio response to a file
with open("output.wav", "wb") as f:
    f.write(response.content)

Request Parameters (form-data)

Parameter	Type	Description	Default
text	string	Text to convert to speech	Required
temperature	float	Generation temperature (higher = more random)	0.2
top_p	float	Top-p sampling parameter	0.95
max_new_tokens	integer	Maximum number of tokens to generate	1400
source_vc_file	file	Source voice file (WAV format)	Optional
source_vc_text	string	Text to convert to speech for source voice	Required if source_vc_file is provided

Best Practices

• Use proper punctuation for better speech synthesis
• Keep sentences natural and conversational
• For long text, consider breaking it into smaller segments
• Adjust temperature and top_p parameters to control voice style:
  • Lower temperature (0.1-0.5): More consistent, stable voice
  • Higher temperature (0.6-1.0): More expressive but less predictable