Text-to-Speech
Convert text to natural-sounding speech using Kokoro TTS on GPU — multiple voices, adjustable speed.
/v1/audio/synthesize
curl "https://audio.toolkitapi.io/v1/audio/synthesize?text=Hello%20world&voice=en_female&speed=1.0&output_format=mp3"
import httpx
resp = httpx.get(
"https://audio.toolkitapi.io/v1/audio/synthesize?text=Hello%20world&voice=en_female&speed=1.0&output_format=mp3",
)
print(resp.json())const resp = await fetch("https://audio.toolkitapi.io/v1/audio/synthesize?text=Hello%20world&voice=en_female&speed=1.0&output_format=mp3", {
});
const data = await resp.json();
console.log(data);# See curl example{
"status": "ok",
"audio_url": "https://storage.example.com/audio/abc123.mp3",
"format": "mp3",
"sample_rate": 24000,
"duration_seconds": 1.5,
"task_id": "abc123"
}Try It Live
Description
How to Use
1. Provide the text to synthesize in the `text` parameter (up to 5000 characters).
2. Select a voice with the `voice` parameter (e.g., `en_female`, `en_male`).
3. Optionally adjust playback speed with the `speed` parameter (0.5× to 2.0×).
4. Choose an output format: `mp3` (default, best compatibility), `wav` (lossless), or `ogg`.
About This Tool
Convert text into natural-sounding speech using Kokoro TTS running on GPU. Choose from multiple voice options and adjust playback speed. Output formats include WAV, MP3, and OGG.
Kokoro TTS produces high-quality, natural-sounding speech suitable for voiceovers, accessibility, and conversational AI applications.
Why Use This Tool
- Voiceovers — Generate narration for videos and presentations
- Accessibility — Convert written content to speech for visually impaired users
- Chatbots — Add voice responses to conversational AI
- E-learning — Create audio versions of educational content
Frequently Asked Questions
How long does generation take?
Can I use custom voices?
What's the maximum text length?
Start using Text-to-Speech now
Get your free API key and make your first request in under a minute.