Audio · Text-to-speech · Released Mar 2025
OpenAI GPT-4o Mini TTS
OpenAI's steerable speech model: ten natural voices you can direct with free-text instructions for tone, accent and pacing.
GPT-4o Mini TTS is a cloud text-to-speech model from OpenAI. It converts written text into natural, spoken audio. It offers a choice of 10 voices. Voices can be tuned for speed. It runs through OpenAI using your own API key, from $0.015 per 1,000 characters.
Specs
- Released
- 1 year ago (Mar 2025)
- Pricing
- $0.015 / 1k chars
- Type
- Text-to-speech
- Voices
- 10 to choose from
- Voice controls
- Speed
About the creator
OpenAI
OpenAI builds GPT, DALL·E, the Sora family, and the open-weight gpt-oss models, and has been a central force behind the modern wave of generative AI.
openai.com ↗More from OpenAI
GPT 6 Astra
TextCloud
OpenAI's flagship GPT-6 model for complex reasoning, coding, research, and long-running agent work, with vision and a 1M-token context window.
GPT 6 Sol
TextCloud
OpenAI's cost-efficient high-end GPT-6 tier for demanding coding and agentic work, with vision and a 1M-token context window.
GPT 6 Sol Pro
TextCloud
GPT 6 Sol in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.
GPT 6 Luna
TextCloud
OpenAI's fast, low-cost GPT-6 tier for high-volume chat, classification, and light agentic work, with vision.
GPT 6 Luna Pro
TextCloud
GPT 6 Luna in OpenAI's pro reasoning mode, which works longer on each answer for higher quality on hard tasks.
GPT 5.4
TextCloud
OpenAI's frontier model with advanced reasoning and broad multimodal capabilities.
From the blog