> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/chatbot/toolkit/speech-to-text.md).

# Speech to Text

The Speech-to-Text tool lets you interact with the chatbot using your voice — either by dictating prompts directly via microphone, transcribing external audio from a URL, or uploading audio files directly. All Speech-to-Text features are accessible inside the Chatbot.

***

#### Voice Prompting via Microphone

*Available on all plans — no extra credit cost*

Instead of typing your prompt, speak it. Qolaba transcribes your voice input and places the text directly into the prompt box — ready to review and send.

**How to use:**

1. Click the **Mic button** next to the Send button in the chat interface
2. Speak your prompt clearly
3. Click **Confirm** to transcribe or **Cancel** to discard
4. The transcribed text appears in the prompt box — edit if needed, then send

***

#### Audio URL Transcription

*Available on Pro plan*

Paste any valid audio URL directly into the chat and request a transcription. The model processes the link and returns a full text transcription of the audio.

**How to use:**

1. Toggle **Speech-to-Text** on in the Toolkit panel
2. Paste your audio URL into the chat prompt
3. Request a transcription — e.g., *"Transcribe this audio"*

**Example prompt:**

```
Transcribe this podcast episode and summarize the key points:
https://example.com/podcast-episode.mp3
```

Common use cases:

* Podcast transcription
* Recorded meeting and lecture notes
* Interview and research audio transcription

***

#### Direct Audio File Upload

*Available on Pro plan*

Upload MP3 or WAV files directly into the chat for instant transcription — no URL required.

**How to use:**

1. Toggle **Speech-to-Text** on in the Toolkit panel
2. Click the **attachment icon** or **Plus (+) icon** in the prompt input area
3. Select your MP3 or WAV file
4. Request a transcription — e.g., *"Transcribe this file"*