OpenAI Text-to-Speech (gpt-4o-mini-tts)
Steerable TTS via /v1/audio/speech: you pass natural-language 'instructions' for tone and style. Output streams over chunked HTTP; there is no text-input WebSocket for TTS (use the Realtime API for that).
Overview
Best for: Teams already on OpenAI that want steerable, prompt-styled speech for non-interactive or sentence-chunked use.
At a glance
$15/1M is tts-1 (tts-1-hd $30/1M). gpt-4o-mini-tts is token-billed ($12 per 1M audio tokens). HTTP chunked and SSE only; full text needed up front. tts-1 has 9 voices, gpt-4o-mini-tts has more. Custom voices limited to eligible customers with consent. No mulaw output (PCM is 24 kHz).
Text plus optional free-text instructions
mp3 (default), opus, aac, flac, wav, pcm (24 kHz 16-bit LE, headerless)
Follows Whisper language support; voices optimised for English
13 built-in (alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, verse, marin, cedar); custom voices for eligible customers with a consent recording
No numeric TTFB claim on the guide; WAV/PCM recommended for fastest first bytes.
Not specified
OpenAI platform terms; disclosure of AI voice required by usage policy.
Features
- output streaming
- style instructions (tone, accent, whispering, speed)
- custom voices (eligible customers, consent required)
- OpenAI-compatible endpoint copied by many vendors
Pricing
| What | Price | Unit |
|---|---|---|
| gpt-4o-mini-tts text input | $0.60 | per 1M text tokens |
| gpt-4o-mini-tts audio output | $12.00 | per 1M audio tokens |
| tts-1 | $15.00 | per 1M characters |
| tts-1-hd | $30.00 | per 1M characters |
900 chars/min for tts-1 ($15/1M) and tts-1-hd ($30/1M). gpt-4o-mini-tts is token-billed; OpenAI no longer shows a per-minute estimate on the pricing page (an earlier page estimated about $0.015/min, unverified now).
Free tier: None specific to TTS
Source: developers.openai.com
Setup
- Create an API key.
- Call POST https://api.openai.com/v1/audio/speech with model, voice, input and optional instructions.
- Use response_format pcm or wav and iterate the streamed body.
- Chunk long LLM output into sentences yourself (no input streaming).
Endpoint
https://api.openai.com/v1/audio/speechAuthentication
Authorization: Bearer <OPENAI_API_KEY>
Quick start python
# pip install openai
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
with client.audio.speech.with_streaming_response.create(
model="gpt-4o-mini-tts",
voice="marin",
input="Hello! Your order has shipped and should arrive on Tuesday.",
instructions="Warm, upbeat customer-support tone.",
response_format="pcm", # 24 kHz 16-bit mono, no header
) as resp:
with open("out_24k_s16le.pcm", "wb") as f:
for chunk in resp.iter_bytes(4096):
f.write(chunk) # or feed to a player as it arrivesWritten from the current docs. Check the vendor's SDK version before you ship.
Warnings
No text-input streaming
/v1/audio/speech needs the full input up front. For LLM token streams you must split into sentences and fire one request per sentence (watch rate limits), or use the Realtime API instead.
Instruction-following varies by snapshot
Developers report the 2025-12-15 snapshot follows style instructions (e.g. whispering) less consistently than 2025-03-20. Pin a dated snapshot and test your prompts.
Token billing makes cost harder to predict
gpt-4o-mini-tts bills audio output tokens, so slower speech or long pauses cost more than the character count suggests. Measure on your own content.
Disclosure is required
OpenAI usage policies require telling end users the voice is AI-generated. Custom voices need a recorded consent statement from the speaker.
Legacy models have fewer voices
tts-1 and tts-1-hd support only 9 voices; marin and cedar are gpt-4o-mini-tts only.
Plus 12 warnings that apply to all text-to-speech, streaming APIs. See category warnings.
Limits
- gpt-4o-mini-tts max 2,000 input tokens per request
- Rate limits by tier: Build 2,000 RPM / 150K TPM; Launch 10,000 RPM / 2M TPM; Grow 10,000 RPM / 8M TPM
Models and products
| Name | Status |
|---|---|
| gpt-4o-mini-tts (alias -> gpt-4o-mini-tts-2025-12-15) | GA |
| gpt-4o-mini-tts-2025-03-20 | Older snapshot |
| tts-1 | GA (legacy) |
| tts-1-hd | GA (legacy) |
Docs and sources
Docs
Sources used
- developers.openai.com/api/docs/pricing
- developers.openai.com/api/docs/guides/text-to-speech
- developers.openai.com/api/docs/models/gpt-4o-mini-tts
- developers.openai.com/docs/changelog
Per-minute cost for gpt-4o-mini-tts; deprecation date of the 2025-03-20 snapshot; SSE stream_format option.