> For the complete documentation index, see [llms.txt](https://docs.aimlapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aimlapi.com/api-references/speech-models/speech-to-text/google/gemini-3.5-transcribe.md).

# Gemini 3.5 Transcribe

{% columns %}
{% column width="66.66666666666666%" %}
{% hint style="info" %}
This documentation is valid for the following list of our models:

* `google/gemini-3.5-transcribe`
  {% endhint %}
  {% endcolumn %}

{% column width="33.33333333333334%" %} <a href="https://aimlapi.com/app/google/gemini-3.5-transcribe" class="button primary">Try in Playground</a>
{% endcolumn %}
{% endcolumns %}

## Model Overview

Gemini 3.5 Transcribe is Google’s speech-to-text model for recorded audio: automatic detection of 85+ languages including mixed-language speech, speaker labels for up to 8 speakers, word-level timestamps, custom vocabulary, and a smart mode that removes filler words and formats the text. Files up to 20 MB and one hour of audio (30 minutes with speaker labels or word timestamps).

{% hint style="success" %}
[Create AI/ML API Key](https://aimlapi.com/app/keys)
{% endhint %}

<details>

<summary>How to make the first API call</summary>

**1️⃣ Required setup (don’t skip this)**\
▪ **Create an account:** Sign up on the AI/ML API website (if you don’t have one yet).\
▪ **Generate an API key:** In your account dashboard, create an API key and make sure it’s **enabled** in the UI.

**2️ Copy the code example**\
At the bottom of this page, pick the snippet for your preferred programming language (Python / Node.js) and copy it into your project.

**3️ Update the snippet for your use case**\
▪ **Insert your API key:** replace `<YOUR_AIMLAPI_KEY>` with your real AI/ML API key.\
▪ **Select a model:** set the `model` field to the model you want to call.\
▪ **Provide input:** fill in the request input field(s) shown in the example.

**4️ (Optional) Tune the request**\
See the API schema below for optional generation settings.

**5️ Run your code**\
Run the updated code in your development environment.

{% hint style="success" %}
For a detailed walkthrough, use our [Quickstart guide](https://docs.aimlapi.com/quickstart/setting-up).
{% endhint %}

</details>

## API Schema

## POST /v1/stt/create

>

```json
{"openapi":"3.0.0","info":{"title":"AIML API","version":"1.0.0"},"servers":[{"url":"https://api.aimlapi.com"}],"paths":{"/v1/stt/create":{"post":{"operationId":"_v1_stt_create","requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"model":{"type":"string","enum":["google/gemini-3.5-transcribe"]},"url":{"type":"string","format":"uri","description":"URL of the input audio file. Provide either url or audio — exactly one is required, not both."},"audio":{"type":"string","description":"The audio file to transcribe. Provide either url or audio — exactly one is required, not both. Up to 20 MB.","format":"binary"},"language_codes":{"type":"array","items":{"type":"string","minLength":1},"maxItems":100,"description":"BCP-47 codes of the languages spoken in the audio, for example [\"he-IL\"] or [\"en-US\", \"es-ES\"]. Omit them to detect the language automatically (85+ languages, mixed-language speech included)."},"custom_vocabulary":{"type":"array","items":{"type":"string","minLength":1},"maxItems":1000,"description":"Up to 1,000 names, acronyms or terms to bias recognition toward (best results with up to 100). Cannot be combined with diarization or word_timestamps."},"diarization":{"type":"boolean","description":"Split the transcript into speaker turns labelled spk_1, spk_2, … (up to 8 speakers; 3 or more is experimental). Audio is then limited to 30 minutes."},"word_timestamps":{"type":"boolean","description":"Return start and end times for every word. May lower accuracy; audio is then limited to 30 minutes."},"mode":{"type":"string","enum":["verbatim","smart"],"description":"\"verbatim\" (the default) keeps every spoken word, fillers included. \"smart\" removes fillers and false starts, applies self-corrections and formats lists, numbers and dates; it cannot be combined with diarization or word_timestamps."}},"required":["model"],"title":"google/gemini-3.5-transcribe"}}}},"responses":{"200":{"content":{"application/json":{"schema":{"type":"object","properties":{"generation_id":{"type":"string"}},"required":["generation_id"]}}},"description":"Successful response."}}}}}}
```

## Code Example

{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}

```python
import requests

response = requests.post(
    "https://api.aimlapi.com/v1/stt/create",
    headers={
        "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type": "application/json",
    },
    json={'model': 'google/gemini-3.5-transcribe'},
)

print(response.json())
```

{% endcode %}
{% endtab %}

{% tab title="JavaScript" %}
{% code overflow="wrap" %}

```javascript
const response = await fetch('https://api.aimlapi.com/v1/stt/create', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "google/gemini-3.5-transcribe"
}),
});

console.log(await response.json());
```

{% endcode %}
{% endtab %}
{% endtabs %}

<details>

<summary>Response</summary>

{% code overflow="wrap" %}

```json
{
  "generation_id": "<generation_id>",
  "model": "google/gemini-3.5-transcribe"
}
```

{% endcode %}

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.aimlapi.com/api-references/speech-models/speech-to-text/google/gemini-3.5-transcribe.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.