# OpenAI (/en/ai/platform/models/asr/openai)

> For AI agents: see the complete documentation index at [llms.txt](/llms.txt).

> Documentation: Conversational AI.
> Documentation version: Preview.
> This document describes only this version. [Version index](/llms/doc-versions-convoai-guides-v2.txt).


OpenAI provides real-time speech-to-text with low latency and reliable performance, making it ideal for conversational AI applications.

## Sample configuration

The following example shows how to configure OpenAI ASR as the agent's ASR when you create or update an agent. For a complete example, see [Create an agent and start a session](/en/ai/platform/get-started/start-stop-agent#create-an-agent).

OpenAI ASR supports BYOK only. It isn't available in managed mode. Store your OpenAI API key in a secret set, and refer to it from the agent. For details, see [Use your own provider keys](/en/ai/platform/build/use-your-own-keys).

**Python SDK**

```python
from agora_agent import Agent, OpenAISTT, secret_ref

# client is your configured Agora client
agent = (
    Agent(client=client)
    .with_stt(
        OpenAISTT(
            api_key=secret_ref("support_prod", "openai"),
            model="gpt-4o-mini-transcribe",
            prompt="Please transcribe the following audio into text. Output in English.",
            language="en",
        )
    )
    .with_llm(...)  # configure your LLM vendor
    .with_tts(...)  # configure your TTS vendor
)
```

**TypeScript SDK**

```ts
import { Agent, OpenAISTT, secretRef } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(
    new OpenAISTT({
      apiKey: secretRef('support_prod', 'openai'),
      model: 'gpt-4o-mini-transcribe',
      prompt: 'Please transcribe the following audio into text. Output in English.',
      language: 'en',
    }),
  )
  .withLlm(/* configure your LLM vendor */)
  .withTts(/* configure your TTS vendor */);
```

**Go SDK**

```go
// client is your configured Agora client
agent := agentkit.NewAgent(client).
	WithStt(vendors.NewOpenAISTT(vendors.OpenAISTTOptions{
		APIKey:   agentkit.SecretRef("support_prod", "openai"),
		Model:    "gpt-4o-mini-transcribe",
		Prompt:   "Please transcribe the following audio into text. Output in English.",
		Language: "en",
	})).
	WithLlm( /* configure your LLM vendor */ ).
	WithTts( /* configure your TTS vendor */ )
```

**REST API**

Set `credential.mode` to `byok` and `credential.fields.api_key` to a reference to your OpenAI API key in a secret set. In the following example, the key is stored as `openai` in the `support_prod` set:

```json
"asr": {
  "credential": {
    "mode": "byok",
    "fields": {
      "api_key": "$secrets.support_prod.openai"
    }
  },
  "vendor": "openai",
  "language": "en-US",
  "params": {
    "input_audio_transcription": {
      "model": "gpt-4o-mini-transcribe",
      "prompt": "Please transcribe the following audio into text. Output in English.",
      "language": "en"
    }
  }
}
```

## Key parameters

The `asr` block takes the following fields. In the SDKs, `OpenAISTT` sets the transcription model, prompt, and language in `params.input_audio_transcription`, and passes any other OpenAI ASR parameters from its additional parameters option to `params`.

**asr required**

**`vendor` (string) required**

Set to `openai`.

**`credential` (object) required**

How the agent authenticates with OpenAI. Set `mode` to `byok` and `fields.api_key` to a `$secrets.<set>.<key>` reference to your OpenAI API key.

**`language` (string) optional**

The language of the user's speech, for example, `en-US`.

**`params` (object) required**

**`input_audio_transcription` (object) required**

The configuration object for audio transcription. Use this object to specify the model, prompt, and language for the transcription task.

**`model` (string) required**

The OpenAI ASR model to use for transcription. For example, `gpt-4o-mini-transcribe`.

**`prompt` (string) required**

A prompt that guides the transcription process. Use this parameter to provide context or instructions for how the audio should be transcribed.

**`language` (string) required**

The language code to use for transcription. For example, use `en` for English.

> **Caution**
>
> The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in `params` are passed through directly to OpenAI without validation. For a full list of supported options, refer to the [OpenAI documentation](https://platform.openai.com/docs/guides/speech-to-text).

This integration is fully supported for use with the Conversational AI Platform. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.