# Bark - Core.Today AI API

> Suno's text-prompted generative audio model. Produces speech with nonverbal sounds like [laughs] and [sighs], plus music and sound effects, in 100+ speaker presets across 13 languages. Returns audio plus an optional .npz history file for voice continuity.

- **Provider**: Suno
- **Model ID**: suno-ai/bark
- **Category**: Audio & TTS
- **Credits**: 190 per generation
- **Speed**: Slow
- **Quality**: Standard

## Features
- Speech with nonverbal sounds: [laughs], [sighs], [gasps]
- Music notes (♪) and sound effect generation
- 131 speaker presets across 13 languages
- History prompts for voice continuity across segments
- Text-prompted generative audio beyond plain TTS

## Use Cases
- Character voices with laughter and emotion
- Creative audio sketches and memes
- Multilingual speech prototypes
- Sound effect generation
- Sung or hummed audio snippets

## 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

### Optional
- **prompt**: string (default: Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.) - Input prompt. Supports [laughs], [sighs], [music], ♪ for singing, and CAPS for emphasis
- **history_prompt**: string - Speaker preset for audio cloning — 131 options like en_speaker_0..9, ko_speaker_0..9, announcer (13 languages)
  Options: announcer, de_speaker_0, de_speaker_1, de_speaker_2, de_speaker_3, de_speaker_4, de_speaker_5, de_speaker_6, de_speaker_7, de_speaker_8, de_speaker_9, en_speaker_0, en_speaker_1, en_speaker_2, en_speaker_3, en_speaker_4, en_speaker_5, en_speaker_6, en_speaker_7, en_speaker_8, en_speaker_9, es_speaker_0, es_speaker_1, es_speaker_2, es_speaker_3, es_speaker_4, es_speaker_5, es_speaker_6, es_speaker_7, es_speaker_8, es_speaker_9, fr_speaker_0, fr_speaker_1, fr_speaker_2, fr_speaker_3, fr_speaker_4, fr_speaker_5, fr_speaker_6, fr_speaker_7, fr_speaker_8, fr_speaker_9, hi_speaker_0, hi_speaker_1, hi_speaker_2, hi_speaker_3, hi_speaker_4, hi_speaker_5, hi_speaker_6, hi_speaker_7, hi_speaker_8, hi_speaker_9, it_speaker_0, it_speaker_1, it_speaker_2, it_speaker_3, it_speaker_4, it_speaker_5, it_speaker_6, it_speaker_7, it_speaker_8, it_speaker_9, ja_speaker_0, ja_speaker_1, ja_speaker_2, ja_speaker_3, ja_speaker_4, ja_speaker_5, ja_speaker_6, ja_speaker_7, ja_speaker_8, ja_speaker_9, ko_speaker_0, ko_speaker_1, ko_speaker_2, ko_speaker_3, ko_speaker_4, ko_speaker_5, ko_speaker_6, ko_speaker_7, ko_speaker_8, ko_speaker_9, pl_speaker_0, pl_speaker_1, pl_speaker_2, pl_speaker_3, pl_speaker_4, pl_speaker_5, pl_speaker_6, pl_speaker_7, pl_speaker_8, pl_speaker_9, pt_speaker_0, pt_speaker_1, pt_speaker_2, pt_speaker_3, pt_speaker_4, pt_speaker_5, pt_speaker_6, pt_speaker_7, pt_speaker_8, pt_speaker_9, ru_speaker_0, ru_speaker_1, ru_speaker_2, ru_speaker_3, ru_speaker_4, ru_speaker_5, ru_speaker_6, ru_speaker_7, ru_speaker_8, ru_speaker_9, tr_speaker_0, tr_speaker_1, tr_speaker_2, tr_speaker_3, tr_speaker_4, tr_speaker_5, tr_speaker_6, tr_speaker_7, tr_speaker_8, tr_speaker_9, zh_speaker_0, zh_speaker_1, zh_speaker_2, zh_speaker_3, zh_speaker_4, zh_speaker_5, zh_speaker_6, zh_speaker_7, zh_speaker_8, zh_speaker_9
- **custom_history_prompt**: string - Your own .npz history file for voice continuity (overrides history_prompt)
- **text_temp**: number (default: 0.7) - Text generation temperature (1.0 more diverse, 0.0 more conservative)
- **waveform_temp**: number (default: 0.7) - Waveform generation temperature (1.0 more diverse, 0.0 more conservative)
- **output_full**: boolean (default: false) - Also return the full generation as a .npz file to reuse as a history prompt

## Examples

### Speech with Laughter
Natural speech with a nonverbal laugh
```json
{
  "model": "suno-ai/bark",
  "input": {
    "prompt": "Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.",
    "history_prompt": "en_speaker_6",
    "text_temp": 0.7,
    "waveform_temp": 0.7
  }
}
```

### Korean Speaker Preset
Korean speech with a Korean speaker preset
```json
{
  "model": "suno-ai/bark",
  "input": {
    "prompt": "안녕하세요? 오늘은 날씨가 정말 좋네요. [laughs]",
    "history_prompt": "ko_speaker_0"
  }
}
```

## 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
- Wrap nonverbal cues in brackets: [laughs], [sighs], [clears throat], [gasps]
- Surround lyrics with ♪ to make Bark sing them
- Pick a language-matched speaker preset (e.g. ko_speaker_0..9 for Korean)
- Set output_full: true and reuse the .npz to keep the same voice across segments
- Bark is generative — the same prompt can produce different results; lower temperatures for consistency

## Documentation
https://replicate.com/suno-ai/bark