---
title: "Speech-to-text input"
slug: "speech-to-text-input"
status: "update"
updated: 2026-09-18T14:43:18Z
published: 2026-09-18T14:43:18Z
canonical: "support.tulip.co/speech-to-text-input"
---

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

# Speech-to-text input

The Speech-to-text Input Widget works alongside all other inputs to allow your users to enter data into your Tulip applications. With the Speech-to-text widget, users can describe the issue they are seeing and it will automatically be transcribed.

![Screen Recording 2023-10-11 at 11.02.59 AM (1).gif](https://cdn.document360.io/7c6ff534-cad3-4fc8-9583-912c4016362f/Images/Documentation/Screen%20Recording%202023-10-11%20at%2011.02.59%20AM%20%281%29.gif)

### Example use cases

When combined with other AI Trigger actions, the Speech-to-text widget can be used to radically change the user experience to interact with your systems and processes.

Some example use cases include:

- **Allow users to ask questions to an AI "Expert".** Remove the need to request the assistance of that one employee that can answer any question by allowing users to ask questions directly of the database of past defects.
- **Collect rich user input in seconds.** Collecting meaningful insights from users that have to manually write or type out their findings is a recipe for useless information. Streamline that data collection so data can be collected as fast as it can be explained.
- **Guide users to the right resource.** Often half the battle in a role is understanding who the right person or department to raise an issue. Combine the Speech-to-text input with the [Classify](/r230/docs/classify-trigger-action) trigger to determine the right resource to route feedback to.

## How to

### Variable Mapping

The Speech-to-text widget, like any other input must be mapped to a text variable. When the user speech has been processed, this variable will be populated with the transcribed user input. ![image.png](https://cdn.document360.io/7c6ff534-cad3-4fc8-9583-912c4016362f/Images/Documentation/image%28235%29.png)

### Triggers

The Speech-to-text input can execute a trigger automatically when the user input has been transcribed. This can be used to automatically store this data, run other copilot Actions and more.

![image.png](https://cdn.document360.io/7c6ff534-cad3-4fc8-9583-912c4016362f/Images/Documentation/image%28236%29.png)

### Spoken Language

The spoken language will default to the language set within the player for the logged-in user, but this can be overridden manually.

![image.png](https://cdn.document360.io/7c6ff534-cad3-4fc8-9583-912c4016362f/Images/Documentation/image%28238%29.png)

## Supported languages

Speech-to-text supports the following languages:

- Chinese
- English (US, GB, and AU)
- French (CA and FR)
- German
- Hindi
- Italian
- Japanese
- Korean
- Portuguese
- Spanish
- Thai

## Limits

Warning

Limits are subject to change.

Currently, the following limits exist for the speech-to-text inputs. These limits are tracked on an Instance level.

If these limits are exceeded, the speech-to-text input may not transcribe the user input.

|  | Limit |
| --- | --- |
| Maximum recording length | 30 seconds |
| Monthly limit | 5,000 requests per month |
| Rate limit | 10 requests per minute |

For additional limits, including account usage, see [Tulip AI usage and pricing](https://support.tulip.co/docs/tulip-ai-usage-and-pricing).

---

Did you find what you were looking for?

You can also head to [community.tulip.co](https://community.tulip.co/?utm_source=intercom&utm_medium=article-link&utm_campaign=all) to post your question or see if others have solved a similar topic!

**Input Widget**

**Input widgets** are a set of **Widgets** specifically designed for users to enter information. Input widgets must be associated with a location where the user input is stored.

**Trigger**

**Triggers** are groups of logic that are tied to an app event, such as step open, timer, widget interaction, etc. App builders can add triggers to **widgets**, **machines**, **devices**, **apps**, and **steps**.

**Triggers** can contain **actions**, **transitions**, and **conditions**.

**Actions**

**Actions** are different operations that can be executed in **Triggers. Actions** cannot move users to other apps, or other **steps.**

Many **Actions** can be added to a single **Trigger.**

*ex. Store the value of variable x to table field y, Print app step, Adjust Edge device GPIO pin.*

**Tulip Instance**

A Tulip customer account. Your instance can be found at https://[your-instance].tulip.co

When *your instance* is referenced, we are just talking about your Tulip account on an organization-level, not user-level.