jigsawstack/tts 📝❓ → 🖼️

▶️ 122 runs 📅 Jun 2025 ⚙️ Cog 0.15.8
multilingual multilingual-tts text-to-speech voice-cloning

About

Transform text into natural-sounding human-like AI voices with low latency and exceptional quality.

Example Output

Output

Example output

Performance Metrics

0.83s Prediction Time
6.98s Total Time
All Input Parameters 
{
  "text": "hi there, how are you ?",
  "accent": "en-US-female-27",
  "api_key": "sk_ba8d51db7829aef7ec445bb80dd59b7ff2c320d851eb6ae4cf41aacfab4df81c690774957983ebcc02f08429fccdfe42b4d8ee6a40b404399c10ca3bcabdbb72024KnIELzWIzzblw1gtM6",
  "return_type": "binary"
}
Input Parameters
text Type: stringDefault:
The text to generate speech from. Character Limits: - Standard TTS: 5-1,500 characters - Voice Cloning TTS: 5-500 characters
accent Type: stringDefault: en-US-female-27
Speaker voice accent. Not required if using voice cloning. Over 700 different voices across multiple languages are available.
api_key Type: string
🔐 Your JigsawStack API Key (required)
return_type Default: binary
The specified return type for the response
voice_clone_id Type: string
The unique identifier for a previously cloned voice. When provided, the API will generate speech using this pre-cloned voice profile instead of creating a new one.
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
d606ddfc5e1541356c2095b71d7d8d69c8188867e33ba2f69b9b53d6702c8f36
Version Created
June 24, 2025
Run on Replicate →