F5 TTS API & Playground

Use the F5 TTS (officially known as F5-TTS) API via PiAPI to clone voices from a reference audio sample and generate natural, high-quality speech audio from text.

F5 TTS Zeroshot Text-to-Speech Playground

Zeroshot text-to-speech with voice cloning using reference audio via the F5-TTS API on PiAPI.

Configuration

Select the model for content generation.

Text that will be converted into speech (max 10,000 characters).

📁

Upload Files

Click or drag a file (JPEG, JPG, PNG)

Preview Example

Example audio for Reference audio (for reference only)

Upload a reference audio file (or provide a URL) for the voice you want F5-TTS to clone.

Result

Idle

This shows preset sample previews. Sign in and click 'Generate audio' to create your own.

Logs

No logs yet

F5 TTS API Features

Seamless Integration
Call the F5 TTS AI API with a simple POST request, using standard JSON fields for model and input, and plug it into your existing backend or workflows in minutes.
Batch Processing
Process many text snippets in parallel by queuing multiple F5-TTS tasks, ideal for audiobooks, support responses, localization, or any high-volume text-to-speech workloads.
High-Quality Results
Zero-shot voice cloning with F5 text API produces natural, expressive speech that closely matches your reference voice sample for production-ready audio.

F5 TTS API Pricing

"Pay-as-you-go" Option

For the most updated unit pricing, please see our pricing page for more details.

ServicePrice (USD)
Text-to-Speech$0.025 per 1000 characters

F5 TTS AI API Frequently Asked Questions