gpt-4o-mini-tts

gpt-4o-mini-tts is a model identifier for text-to-speech. The model is used to generate natural speech from text, which can serve barrier-free reading, voice broadcast, customer service voice, learning content and multimedia narration. When adapting, you should first verify the target language, pronunciation, speaking speed, pauses, emotional expression, audio format and cost, and establish a pronunciation test set for numbers, dates, names and professional terms. If you use real people's voices, personal recordings, or commercial audio, you should obtain the necessary authorization and comply with the voice synthesis labeling requirements.

Context

16000 tokens

Max output

2000 tokens

Input

llm

Output

text-to-speech