GPT Realtime Translate is an audio-to-audio translation model built for low-latency voice conversations. Reach for it when you need to translate spoken input into localized audio while preserving the original speaker's vocal tone.
Modalities
Text → Audio
Price
$0.0459 / min
Speed
fast
Pricing
Per minute of audio processed. Min billable: 1 minute.
$0.0459 / minWhen to use GPT Realtime Translate
Where this model earns its cost — and where it doesn't.
The model accepts raw audio input and returns translated audio output without intermediate text conversion. It supports voice cloning across 13 languages: Spanish, Portuguese, French, Japanese, Russian, Chinese, German, Korean, Hindi, Indonesian, Vietnamese, Italian, and English.
On Kyma, it operates as a realtime websocket connection billed per minute. Requests automatically failover if a serving path degrades, and every response includes the exact cost in usage.cost alongside an X-Kyma-Model header. Prompt caching bills repeated prompt prefixes at 10% of the input rate.
It is strictly an audio modality model with a 3600-token context window. It does not support text inputs, vision, structured outputs, or explicit reasoning steps, and runs on a premium cost tier with fast inference speeds.
Live Cross-Language Calls
Translates spoken audio in real time while maintaining the original speaker's voice characteristics.
Automated Media Dubbing
Generates localized audio tracks that match the source speaker's tone and pacing.
Multilingual Voice Agents
Powers conversational bots that listen and reply in translated audio without text intermediaries.
Real-Time Meeting Translation
Streams live audio translation for international team discussions and broadcasts.
Not ideal for: Do not use this model for text-based tasks, vision analysis, structured data extraction, or workflows requiring explicit reasoning steps.
Quick start
Up and running in under two minutes.
- 1
Create an API key
Sign up and grab a key from the dashboard — $0.50 free credit, no card required.
Get API key → - 2
Make your first request
Drop in your key and send a chat completion — fully OpenAI-compatible.
curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-realtime-translate", "messages": [ {"role": "user", "content": "Explain prompt caching in one paragraph."} ] }' - 3
Stream responses
Add
"stream": trueto receive tokens as they arrive.curl https://kymaapi.com/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-realtime-translate", "stream": true, "messages": [{"role": "user", "content": "Hello!"}] }'
FAQ
Common questions about this model.
How much does GPT Realtime Translate cost?
How do I use GPT Realtime Translate?
How is this model billed on Kyma?
Can I cache prompts to reduce costs?
Does it support text or vision inputs?
More models by OpenAI
See all 11 →| Model | Context | Input | Output |
|---|---|---|---|
GPT-5.6 Terra | 1M | $1.443 | $8.656 |
GPT-5.6 Luna | 1M | $0.1373 | $0.8231 |
GPT-5.6 Luna Pro | 1M | $0.135 | $0.81 |
GPT-5.6 Terra Pro | 1M | $1.35 | $8.10 |
GPT-5.6 Sol | 1M | $6.75 | $40.50 |
GPT-5.6 Sol Pro | 1M | $6.75 | $40.50 |
GPT Image 2 | — | $0.081 / image | |
GPT-OSS 120B | 128K | $0.0527 | $0.2565 |
