# Chatterbox Multilingual - Core.Today AI API > Chatterbox open-source TTS in 23 languages with instant voice cloning and emotion exaggeration control. Max 300 characters per request. - **Provider**: Resemble AI - **Model ID**: resemble-ai/chatterbox-multilingual - **Category**: Audio & TTS - **Credits**: 7 per generation (max 300 characters) - **Speed**: Fast - **Quality**: High ## Features - 23 language support including Korean - Instant voice cloning from short audio - Emotion exaggeration control - Language transfer with cloned voices - Fixed low price per generation ## Use Cases - Multilingual short-form narration - Localized voice messages - Cross-language voice cloning - International IVR prompts - Language learning audio ## API Endpoint Base URL: https://api.core.today/v1 Create Prediction: POST /predictions Get Status: GET /predictions/{job_id} ## Authentication Header: X-API-Key: YOUR_API_KEY ## Input Parameters ### Required - **text**: string - Text to synthesize (maximum 300 characters) ### Optional - **language**: string (default: en) - Language for synthesis (23 languages) Options: ar, da, de, el, en, es, fi, fr, he, hi, it, ja, ko, ms, nl, no, pl, pt, ru, sv, sw, tr, zh - **reference_audio**: string - Reference audio for voice cloning (optional). Defaults to the language's default voice - **exaggeration**: number (default: 0.5) - Speech expressiveness (0.25-2.0). Neutral = 0.5 - **temperature**: number (default: 0.8) - Controls randomness (0.05-5.0) - **cfg_weight**: number (default: 0.5) - Generation guidance (0.2-1.0). Use 0.5 for balance, 0 for language transfer - **seed**: integer (default: 0) - Random seed (0 for random) ## Examples ### Korean Voice Message Short Korean announcement with the default voice ```json { "model": "resemble-ai/chatterbox-multilingual", "input": { "text": "안녕하세요, 코어닷투데이입니다. 오늘도 좋은 하루 보내세요!", "language": "ko", "exaggeration": 0.5 } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending | processing | completed | failed", "result": "URL or data (when completed)" } ``` ## Usage Flow 1. POST /predictions with model and input -> receive job_id 2. GET /predictions/{job_id} -> poll until status is completed or failed 3. Result contains output URL(s) ## Tips - Keep text under 300 characters — split longer scripts into multiple requests - Billed a flat 7 credits per generation regardless of text length - Set cfg_weight to 0 when cloning a voice into a different language (language transfer) - For longer text and preset voices, use Chatterbox Turbo instead ## Documentation https://replicate.com/resemble-ai/chatterbox-multilingual