# \[Realtime API\] Why does \`input\_audio\_transcription\` usage include \`text\_tokens\`?

**URL:** <https://community.openai.com/t/realtime-api-why-does-input-audio-transcription-usage-include-text-tokens/1362434>\
**Category:** API\
**Tags:** api\
**Created:** [October 14, 2025, 10:32am UTC](https://community.openai.com/t/realtime-api-why-does-input-audio-transcription-usage-include-text-tokens/1362434 "2025-10-14T10:32:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![HBD007](https://avatars.discourse-cdn.com/v4/letter/h/97f17d/32.png) [@HBD007](https://community.openai.com/u/HBD007)\
**Post date:** [October 14, 2025, 10:32am UTC](https://community.openai.com/t/realtime-api-why-does-input-audio-transcription-usage-include-text-tokens/1362434/1 "2025-10-14T10:32:21Z")

</div>

### Summary

I’m using the **Realtime API in conversation mode** (not transcription-only mode) with `input_audio_transcription` enabled to get parallel transcription of user audio input. The model is `gpt-4o-mini-transcribe`.

I notice that the `conversation.item.input_audio_transcription.completed` event always includes **`text_tokens: 1`** in the usage breakdown, even though I’m only sending audio data (no text messages).

I’d like to understand what these text tokens represent and whether this is expected behavior.

### Configuration

My Realtime API session configuration (via `session.update`):

```json
{
  "type": "session.update",
  "session": {
    "model": "gpt-realtime-2025-08-28",
    "modalities": ["text"],
    "input_audio_transcription": {
      "model": "gpt-4o-mini-transcribe",
      "language": "ja"
      // Note: No "prompt" parameter specified (empty/default)
    },
    "turn_detection": {
      "type": "server_vad"
    }
  }
}

```

The Realtime session is used for conversation (function calling), and `input_audio_transcription` provides parallel transcription for logging purposes.

**Important** : I’m **not** providing a `prompt` parameter in the transcription config, so the text tokens cannot be from a custom prompt.

### Observed Usage Data

Every transcription event shows a consistent pattern:

```json
{
  "type": "conversation.item.input_audio_transcription.completed",
  "transcript": "七丸。",
  "usage": {
    "type": "tokens",
    "total_tokens": 16,
    "input_tokens": 11,
    "input_token_details": {
      "text_tokens": 1, // ← Always 1 (even with no prompt!)
      "audio_tokens": 10
    },
    "output_tokens": 5
  }
}

```

**Observation** : The `text_tokens: 1` appears consistently across all transcription events, regardless of:

- Audio content (different utterances)
- Transcription length (output\_tokens vary, but input text\_tokens is always 1)
- No custom prompt being provided

### Questions

1. **What do these `text_tokens` represent?**

2. **Is this documented anywhere?**

3. **Should I expect this value to always be 1?**

### Context

In the Realtime API, I receive two separate usage reports:

1. `response.done` events with usage for the main conversation (Realtime model)
2. `conversation.item.input_audio_transcription.completed` events with usage for transcription (gpt-4o-mini-transcribe)

Understanding what the `text_tokens` in the transcription usage represent helps me:

- Calculate accurate transcription costs separately from conversation costs
- Explain billing breakdowns to stakeholders
- Better understand the Realtime API’s token accounting model
- Determine if these tokens are fixed overhead or variable based on configuration

Any insights would be greatly appreciated! 🙏

* * *