Skip to main content
Fish AudioFastHigh

Fish Speech

High-quality multilingual text-to-speech with natural prosody and voice cloning capabilities.

5 credits
per 1000 characters
Natural prosody
Multiple languages
Voice cloning
Emotional control
Fast synthesis

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
  "model": "fish-speech",
  "input": {
    "text": "Welcome to our product introduction. Today, we'll explore the features that make our solution stand out.",
    "language": "en"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
textstringYes-Text to convert to speech
reference_audiostringNo-URL for voice cloning reference
languagestringNoautoTarget language
autoenkojazhesfrde

Examples

Narration

Create natural narration

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
  "model": "fish-speech",
  "input": {
    "text": "Welcome to our product introduction. Today, we'll explore the features that make our solution stand out.",
    "language": "en"
  }
}'

Tips & Best Practices

1Use reference audio for consistent voice
2Include punctuation for natural pauses
3Works great for Korean and English

Use Cases

Podcast generation
Audiobook narration
Video voiceovers
Virtual assistants
Content localization

Model Info

ProviderFish Audio
Version1.5
CategoryAudio & TTS
Price5 credits

API Endpoint

POST /v1/predictions
Try in PlaygroundBack to Docs