> ## Documentation Index
> Fetch the complete documentation index at: https://assemblyai.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# assemblyai-stt-3-7 migration guide

Follow this guide to move from `universal-3-pro`, `universal-3-5-pro`, or `universal-2` to `assemblyai-stt-3-7`.

## Update your speech\_models

**If you don't set `speech_models`**

Your default model may change. Check which model your requests use on the [usage page](https://www.assemblyai.com/dashboard/usage), or send a test request and check which model processed it, as described in [Identify the model used](https://assemblyai.com/docs/pre-recorded-audio/select-the-speech-model.md#identify-the-model-used). Then:

* **`universal-3-5-pro` or `universal-3-pro`:** your requests will automatically use `assemblyai-stt-3-7` starting December 8, 2026. This is a change to the default model, not the retirement of `universal-3-5-pro` or `universal-3-pro`. See [Behavioral changes](#behavioral-changes).
* **`universal-2`:** you won't be upgraded automatically. To upgrade, set `speech_models` to `["assemblyai-stt-3-7", "universal-2"]`. If all your audio is in [languages AssemblyAI-STT-3.7 supports](https://assemblyai.com/docs/pre-recorded-audio/supported-languages.md#assemblyai-stt-37), `["assemblyai-stt-3-7"]` is enough.

**If you set `speech_models`**

You won't be upgraded to the latest model until that model is retired. To migrate now, change the model in `speech_models` to `assemblyai-stt-3-7`:

| Before | After |
| - | - |
| `"speech_models": ["universal-3-5-pro", "universal-2"]` | `"speech_models": ["assemblyai-stt-3-7", "universal-2"]` |
| `"speech_models": ["universal-3-pro", "universal-2"]` | `"speech_models": ["assemblyai-stt-3-7", "universal-2"]` |
| `"speech_models": ["universal-3-5-pro"]` | `"speech_models": ["assemblyai-stt-3-7"]` |
| `"speech_models": ["universal-3-pro"]` | `"speech_models": ["assemblyai-stt-3-7"]` |
| `"speech_models": ["universal-2"]` | `"speech_models": ["assemblyai-stt-3-7", "universal-2"]` |

Keep `universal-2` in the list if you need languages AssemblyAI-STT-3.7 doesn't support. If all your audio is in [languages AssemblyAI-STT-3.7 supports](https://assemblyai.com/docs/pre-recorded-audio/supported-languages.md#assemblyai-stt-37), `["assemblyai-stt-3-7"]` is enough.

```json After theme={null}
{
  "audio_url": "https://assembly.ai/wildfires.mp3",
  "speech_models": ["assemblyai-stt-3-7", "universal-2"],
  "language_detection": true
}
```

```json Before theme={null}
{
  "audio_url": "https://assembly.ai/wildfires.mp3",
  "speech_models": ["universal-3-5-pro", "universal-2"],
  "language_detection": true
}
```

## Behavioral changes

### Model fallback

Previously, AssemblyAI fell back to another model by default. For example, if you used automatic language detection and set `speech_models` to `["universal-3-pro"]` or `["universal-3-5-pro"]`, and AssemblyAI detected a language that the model doesn't support, it automatically transcribed with `universal-2` instead.

Now, when you set `speech_models` to `["assemblyai-stt-3-7"]`, whether AssemblyAI falls back to another model depends on how you set the language:

* **`language_detection: true`**: AssemblyAI always transcribes with AssemblyAI-STT-3.7 and never falls back to another model. To fall back to Universal-2 for detected languages that AssemblyAI-STT-3.7 doesn't support, set `speech_models` to `["assemblyai-stt-3-7", "universal-2"]`.
* **`language_code`**: If you set a language code that AssemblyAI-STT-3.7 doesn't support, AssemblyAI falls back to Universal-2.

To keep the previous fallback behavior, explicitly set `speech_models` to `["assemblyai-stt-3-7", "universal-2"]`:

```json theme={null}
{
  "audio_url": "https://assembly.ai/wildfires.mp3",
  "speech_models": ["assemblyai-stt-3-7", "universal-2"],
  "language_detection": true
}
```

AssemblyAI-STT-3.7 takes priority wherever it appears in `speech_models`. For example, if you add it after an existing model, as in `["universal-2", "assemblyai-stt-3-7"]`, AssemblyAI-STT-3.7 transcribes every language it supports, and Universal-2 handles the rest. If `speech_models` doesn't include `assemblyai-stt-3-7`, the first model in the list, from left to right, that supports the language is used, as before.

See [Transcribe all 99 languages by combining speech models](https://assemblyai.com/docs/pre-recorded-audio/select-the-speech-model.md#transcribe-all-99-languages-by-combining-speech-models) for details.

### Disfluencies

The disfluencies default depends on the speech model. AssemblyAI-STT-3.7 keeps disfluencies by default. Universal-3.5 Pro, Universal-3 Pro, and Universal-2 remove them by default. To get the same behavior on every model, set `disfluencies` explicitly. See [Verbatim](https://assemblyai.com/docs/pre-recorded-audio/include-filler-words.md).

> [!NOTE]
>
> On AssemblyAI-STT-3.7, `disfluencies: true` keeps more than filler words. It also preserves repetitions, stutters, false starts, and informal contractions such as "gonna" and "kinda". On Universal-2, it keeps filler words only. If you process transcript text downstream, check your audio with the new output before you migrate.

When `speech_models` includes `assemblyai-stt-3-7` in any position, `disfluencies` defaults to `true` for the whole request. This includes lists such as `["assemblyai-stt-3-7", "universal-2"]` and `["universal-2", "assemblyai-stt-3-7"]`, even when Universal-2 transcribes the audio.

To keep the default you had on `universal-3-pro` or `universal-3-5-pro` and remove disfluencies, set `disfluencies` to `false`:

```json theme={null}
{
  "audio_url": "https://assembly.ai/wildfires.mp3",
  "speech_models": ["assemblyai-stt-3-7"],
  "disfluencies": false
}
```

### Code switching

AssemblyAI-STT-3.7 handles code switching natively, so you don't need to turn it on. The `code_switching` and `code_switching_confidence_threshold` options in `language_detection_options` apply only to Universal-2. If your requests set them, they have no effect when AssemblyAI-STT-3.7 transcribes the audio. Keep them only if Universal-2 is in your list and handles some of your languages. See [Code switching](https://assemblyai.com/docs/pre-recorded-audio/code-switching.md).

### Restrict the languages

To limit transcription to a known set of languages on AssemblyAI-STT-3.7, use `language_codes` instead of `language_detection_options.expected_languages`:

```json theme={null}
{
  "audio_url": "https://assembly.ai/wildfires.mp3",
  "speech_models": ["assemblyai-stt-3-7"],
  "language_codes": ["en", "es", "pt"]
}
```

On AssemblyAI-STT-3.7, `language_codes` accepts any number of supported languages, and English isn't required. A one-element list such as `["es"]` behaves like setting `language_code` to `"es"`. On Universal-2, `language_codes` accepts at most two languages, and one of them must be `"en"`. `language_codes` can't be combined with `language_code` or `language_detection`. See [Constrain the language set](https://assemblyai.com/docs/pre-recorded-audio/code-switching.md#constrain-the-language-set).
