All Models


Audio
🐟
Fish Audio TTS
Fish Audio
About
Fish Audio TTS provides natural-sounding text-to-speech synthesis at an accessible price point, making it ideal for developers and content creators who need reliable voice generation at scale. Strong multilingual support and natural prosody make it suitable for a wide range of applications without breaking the budget.
Pricing Tiers
| Resolution / Tier | Cost | Credits |
|---|---|---|
| Standard / 1M characters | $19.000/req | 4104 cr |
Use Cases
Developer voice integrationPodcast and content voiceoverMultilingual app supportEducational content narration
API Example
JavaScript
const response = await fetch("https://api.lumavo.com/v1/tts", {
method: "POST",
headers: {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "fish-audio-tts",
text: "Let me tell you a story about the future of artificial intelligence.",
voice: "en-US-casual-1",
language: "en"
})
});
const { taskId } = await response.json();