orpheus-tts — AI Audio Model

Fal

Fal

orpheus-tts

Commercial useaudio

Orpheus TTS is a cutting-edge speech language model, crafted to deliver high-quality and emotionally expressive text-to-speech output. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time performances.

Model Type
coin

Pricing: 0.36 joules / second

Input
Temperature
Temperature for generation (higher = more creative). Default value: 0.7
0.02.0
Repetition penalty
Repetition penalty (>= 1.1 required for stable generations). Default value: 1.2
1.12.0

voice

Default value: "tara"

OutputAUDIO

Output will be displayed here

Fill in the inputs on the left and hit RUN to preview the results.

Examples

Explore different use cases and parameter configurations