GPT 4o Mini Tts
OpenAI
openai/gpt-4o-mini-tts
GPT-4o Mini TTS β expressive, natural speech
Context Window
β
Max Output
β
About this model
GPT-4o Mini TTS is OpenAI's latest text-to-speech model powered by GPT-4o Mini's multimodal capabilities. Compared to TTS-1, it produces more natural, expressive speech with better context understanding and emotion/tone control.
Supports voices: alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer.
Highlights
GPT-4o powered
Emotion control
10 voices
Context-aware
Best For
Voice assistantsAudiobooksPodcastsAccessibility
2025-03-20
Capabilities
TTS
Aliases
gpt-4o-mini-ttsPricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $0.63 |
| Output / 1M | $2.52 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.audio.speech.create( model="openai/gpt-4o-mini-tts", voice="alloy", input="Hello! Welcome to chuizi.ai.", ) response.stream_to_file("output.mp3")