OpenAI · Speech
GPT-4o Mini TTS API price
OpenAI’s GPT-4o Mini TTS through one prepaid, OpenAI-compatible key: $0.015 per 1K characters, the provider’s list price with nothing added per request.
GPT-4o Mini TTS price
- Price
- $0.015per 1K characters
- ≈ $0.015 a minute of speech
OpenAI’s list price, in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.
What GPT-4o Mini TTS is good at
Text in, MP3 out. Ten voices, instructions for tone, 4,000 characters a call.
In short: text in, spoken MP3 out.
Speech model, called at /v1/audio/speech. Listed under text to speech.
GPT-4o Mini TTS endpoint and id
- Provider
- OpenAI
- Type
- Speech
- Endpoint
/v1/audio/speech- Model id
gpt-4o-mini-tts
What GPT-4o Mini TTS costs per request
The list price, multiplied out.
| Minutes of speech | Cost |
|---|---|
| 1 | $0.0150 |
| 60 | $0.9000 |
| 600 | $9.00 |
At $0.015 per 1K characters (≈ $0.015 a minute of speech), OpenAI’s list price.
GPT-4o Mini TTS cost calculator
Set how much you need. The provider bills per unit; this is the arithmetic.
Call GPT-4o Mini TTS with the OpenAI SDK
Base URL https://api.airuntime.dev/v1, your key as the bearer token, and model set to gpt-4o-mini-tts.
curl
curl https://api.airuntime.dev/v1/audio/speech \
-H "Authorization: Bearer $TOKENS_PAY_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4o-mini-tts", "input": "Your credit has arrived.", "voice": "alloy"}' \
--output speech.mp3Python
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.airuntime.dev/v1", api_key=os.environ["TOKENS_PAY_KEY"])
audio = client.audio.speech.create(model="gpt-4o-mini-tts", input="Your credit has arrived.", voice="alloy")
audio.write_to_file("speech.mp3")Node
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airuntime.dev/v1", apiKey: process.env.TOKENS_PAY_KEY });
const audio = await client.audio.speech.create({ model: "gpt-4o-mini-tts", input: "Your credit has arrived.", voice: "alloy" });
fs.writeFileSync("speech.mp3", Buffer.from(await audio.arrayBuffer()));Who processes GPT-4o Mini TTS requests
Your code calls AI Runtime directly. It forwards the request to the provider and keeps only the bill.
Processing and storage
- Model provider
- OpenAI · data terms
- Gateway
- AI Runtime, AWS us-east-1
Not stored by Tokens.Pay or AI Runtime. Prompts and outputs exist in memory only while the request runs; we keep the billing record. The provider processes the request under its own terms. Zero data retention, exactly
Compare GPT-4o Mini TTS with similar models
| Model | Provider | Price |
|---|---|---|
| GPT-4o Mini TTS (this page) | OpenAI | $0.015 per 1K characters |
| Fish S2.1 Pro | Fish Audio | $0.015 per 1K bytes |
| Fish S2.1 Pro Free | Fish Audio | Free per 1K bytes |
GPT-4o Mini TTS API questions
How much does the GPT-4o Mini TTS API cost?
$0.015 per 1K characters, OpenAI’s list price. Tokens.Pay adds nothing per request; a 5% fee (minimum $0.79) applies when you add credit.
What is the model id for GPT-4o Mini TTS?
Send model "gpt-4o-mini-tts" to https://api.airuntime.dev/v1/audio/speech with your Tokens.Pay key as the bearer token. Any OpenAI-compatible SDK works.
Does Tokens.Pay store my GPT-4o Mini TTS prompts?
No. AI Runtime, the gateway your key calls, keeps prompts and outputs in memory only while the request runs and stores just the billing record. The request is processed by OpenAI, under the provider’s own API data terms.
Add credit, then call GPT-4o Mini TTS.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit