Capabilities
Explore what GPT-4o mini TTS (2025-12-15) supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- OpenAI
- Product
- Text-to-Speech
- Release Date
- Dec 15, 2025
- Data Policy
- No training
- Region
- Global
- Input
- Text
- Output
- Audio
Playground
Try GPT-4o mini TTS (2025-12-15) by OpenAI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for GPT-4o mini TTS (2025-12-15).
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| OpenAI | Not specified | Audio | $12.75 / 1M characters | — | openai/gpt-4o-mini-tts-2025-12-15:openai |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 4096 |
| Formats | mp3, opus, aac, flac, wav, pcm |
Provider Notes
All current models support MP3, Opus, AAC, FLAC, WAV, and raw PCM at speeds from 0.25 to 4. gpt-4o-mini-tts and its pinned snapshot accept delivery instructions, all 13 current built-in voices, eligible custom voice IDs, and stream_format=audio or sse. Legacy tts-1 and tts-1-hd reject instructions, custom voices, SSE event framing, and the newer cedar, marin, verse, and ballad voices. OpenAI requires end users to be told that the voice is AI-generated.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o-mini-tts-2025-12-15",
"input": "Make every word count.",
"voice": "auto",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | openai/gpt-4o-mini-tts-2025-12-15 — Required model identifier. |
stream_format | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 4096 |
| Formats | mp3, opus, aac, flac, wav, pcm |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| GPT-4o mini TTSOpenAI | Not specified | $12.75 / 1M characters | — |
| TTS-1OpenAI | Not specified | $12.75 / 1M characters | — |
| TTS-1 HDOpenAI | Not specified | $25.50 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
