Openai: gpt-audio
openai/gpt-audio
Start building free
gpt-audio is an OpenAI model designed for speech and audio understanding and generation, available via the company’s multimodal API lineup. It belongs to the broader GPT family but is specialized for tasks like speech-to-text transcription, audio-based conversation, and voice interaction, with a focus on practical latency and cost for real-time or near–real-time applications. The model is typically used to power voice assistants, call center tools, meeting transcription, and interactive audio experiences, and is intended to plug cleanly into the same workflows as text- and vision-capable GPT models. It emphasizes robust performance on everyday spoken language and usability in production products rather than research-only, cutting‑edge audio benchmarks.
Pricing
Current price per 1,000,000 tokens. Every request is billed automatically from its exact usage.
Included in plans
This model is not included in any plan yet.
Statistics
Live performance and usage of this model, aggregated across all users.
Usage over time
Token usage
Last 30 days- Input tokens
- 0 0%
- Output tokens
- 0 0%
- Avg. input per request
- 0
- Avg. output per request
- 0
- Largest request
- 0 tokens
Reliability
Last 30 days- Successful
- 4 100%
- Failed
- 0 0%
- 200 Success 4 100%
Response time
Successful requests · last 30 daysLast 24 hours
Latency (ms)
Requests per hour
Usage rhythm
Last 30 days · site timezone- Busiest hour: 14:00
- Busiest weekday: Tuesday
- Busiest day: 27 October (3 requests)
All-time record
- Total requests
- 4
- Total tokens
- 0
- Active days
- 2
- First request
- 27 October 2026
- Last request
- 3 هفته ago
API
Turn text into speech and get the audio file back, using your API token.
curl https://apiex.cloud/api/v1/audio/speech \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-audio",
"input": "Hello! This is a test of the text-to-speech API.",
"voice": "alloy"
}' \
--output speech.mp3
Authentication
Every request must include an Authorization: Bearer <TOKEN> header. Generate a token from your account's API Keys page — its access to models is set automatically from your active plans and redeemed codes, and you can set its rate limit and IP restrictions.
| Parameter | Type | Description |
|---|---|---|
model | string, required | This model's ID, exactly as shown above. |
input | string, required | The text to speak. Up to 4,000 characters. |
voice | string, optional | The voice to use. Which voices exist depends on the model. |
Replace YOUR_API_KEY with a token from your account, then see the full API reference for every parameter.
Frequently asked questions
What is gpt-audio?
gpt-audio is an OpenAI model designed for speech and audio understanding and generation, available via the company’s multimodal API lineup. It belongs to the broader GPT family but is specialized for tasks like speech-to-text transcription, audio-based conversation, and voice interaction, with a focus on practical latency and cost for real-time or near–real-time applications. The model is typically used to power voice assistants, call center tools, meeting transcription, and interactive audio experiences, and is intended to plug cleanly into the same workflows as text- and vision-capable GPT models. It emphasizes robust performance on everyday spoken language and usability in production products rather than research-only, cutting‑edge audio benchmarks.
How much does gpt-audio cost?
Input tokens are priced at $3,00 per 1,000,000 tokens and output tokens at $12,00 per 1,000,000 tokens. Pricing is billed automatically per request; no separate plan is required.
What is the context length of gpt-audio?
gpt-audio supports a context window of up to 128,000 tokens.
Does gpt-audio support image input?
gpt-audio currently accepts text input only.
Which provider is gpt-audio from?
gpt-audio is developed by Openai and made available on this gateway through our routing infrastructure.
When was gpt-audio added to this gateway?
gpt-audio has been available on this gateway since September 23, 2026.
Is gpt-audio currently available?
Yes, gpt-audio is active and can be used right now through this gateway.