GPT-4o-mini-TTS is a state-of-the-art text-to-speech (TTS) model built on the GPT-4o mini architecture. It transforms text into high-quality, realistic speech featuring natural intonation and expressiveness. The model offers robust multilingual support and customizable voice parameters, making it ideal for diverse TTS applications.
vs Google WaveNet: Google WaveNet offers extremely high-fidelity audio but lacks GPT-4o-mini’s broad language and customization flexibility. GPT-4o-mini-TTS enables adjustable emotional intonation and real-time streaming, which WaveNet generally does not support.
vs OpenAI Whisper TTS: Whisper TTS focuses primarily on speech recognition with limited TTS development, while GPT-4o-mini-TTS specializes in expressive, multi-language speech synthesis with multiple voice options.
vs Amazon Polly: Amazon Polly provides many voices and languages but is less flexible in real-time streaming and fine control of emotional parameters compared to GPT-4o-mini-TTS. GPT-4o-mini-TTS offers richer customization and open domain adaptability.
vs Microsoft Azure TTS: Azure TTS delivers competitive quality but may have higher latency. GPT-4o-mini-TTS excels in low-latency streaming and supports a larger number of languages and voice customizations.
Accessible via AI/ML API. Documentation: available here.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/tts", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "openai/gpt-4o-mini-tts", "text": "Hello from AI/ML API", "voice": "alloy" }, ) print(r.json()["audio"]) # URL to the generated audio
const r = await fetch("https://api.aimlapi.com/v1/tts", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "openai/gpt-4o-mini-tts", "text": "Hello from AI/ML API", "voice": "alloy" }), }); const { audio } = await r.json(); console.log(audio); // URL to the generated audio
curl -X POST https://api.aimlapi.com/v1/tts \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openai/gpt-4o-mini-tts","text":"Hello from AI/ML API","voice":"alloy"}' # the JSON response contains "audio" — a URL to the generated speech
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
GPT-4o mini TTS This page | Speech synthesis | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
GPT-4o mini TTS takes text as input and returns audio.
GPT-4o mini TTS became available on January 5, 2026.
GPT-4o mini TTS is priced at input $0.78 / 1M characters.
GPT-4o mini TTS was built by OpenAI.
Send a request to https://api.aimlapi.com/v1/tts with openai/gpt-4o-mini-tts as the model id.
Yes. GPT-4o mini TTS is served through AI/ML API, so the same key and endpoint format used for other models applies.
It accepts up to 2000 input tokens per request.
