GPT-4o mini TTS: model ids and price

How to call it

2 ways to use GPT-4o mini TTS, with the model id each provider expects.

Providers, model ids, endpoints and docs for GPT-4o mini TTS
Provider	Model id	Endpoint	Docs
OpenAI API	`gpt-4o-mini-tts`	`https://api.openai.com/v1/audio/speech`	developers.openai.com
Azure OpenAI (Microsoft Foundry)	`gpt-4o-mini-tts`		learn.microsoft.com

Pricing

Prices for GPT-4o mini TTS
Text input	$0.60 per 1M tokens
Audio output	$12 per 1M tokens

As published: “per 1M tokens (USD)”.

Source: developers.openai.com, checked 15 October 2026.

Specs

Input: Text
Output: Audio
Context window: Not published
Max output: Not published
Open weights: No
Licence: Proprietary
Released: 20 March 2025
Status: Deprecated
Type: Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

Steerable speech

Only current OpenAI TTS model listed in the models catalog; max 2000 input tokens.

Source: developers.openai.com
Instruction-steerable voice

An `instructions` field controls accent, emotional range, intonation, impressions, speed, tone and whispering.

Source: developers.openai.com

Notes

Snapshots gpt-4o-mini-tts-2025-03-20 and gpt-4o-mini-tts-2025-12-15 (default). Older tts-1 ($15/1M chars) and tts-1-hd ($30). Deprecated 2026-10-01 (both snapshots, plus tts-1 and tts-1-hd): removal from the API on Jan 6 2027, recommended replacement gpt-realtime-2.1-mini (https://developers.openai.com/api/docs/deprecations).

curl https://api.openai.com/v1/audio/speech \
 -H "Authorization: Bearer $OPENAI_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"gpt-4o-mini-tts","voice":"alloy","input":"Hello"}' --output out.mp3

Sources: