rm dash from universal 3 pro (#601)

Author: MAsuamah

fern/pages/01-getting-started/universal-3-pro.mdx

@@ -1,17 +1,17 @@
 ---
 title: "Introducing Universal-3 Pro"
-subtitle: "Learn how to transcribe pre-recorded audio using Universal-3-Pro."
+subtitle: "Learn how to transcribe pre-recorded audio using Universal-3 Pro."
 hide-nav-links: true
-description: "Learn how to transcribe pre-recorded audio using Universal-3-Pro."
+description: "Learn how to transcribe pre-recorded audio using Universal-3 Pro."
 ---
 
 import { AudioPlayer } from "../../assets/components/AudioPlayer";
 
 ## Overview
 
-Universal-3-Pro is our most powerful Voice AI model yet, designed to capture the "hard stuff" that traditional ASR models struggle with.
+Universal-3 Pro is our most powerful Voice AI model yet, designed to capture the "hard stuff" that traditional ASR models struggle with.
 
-**Key Universal-3-Pro Capabilities:**
+**Key Universal-3 Pro Capabilities:**
 
 - **Keyterm Prompting:** Improve recognition of domain-specific terminology, rare words, and proper nouns
 - **Prompting:** Guide transcription style, formatting, and output characteristics
@@ -32,7 +32,7 @@ The model out of the box outperforms all ASR models on the market on accuracy, e
 
 ## Quick start
 
-This example shows how you can transcribe a pre-recorded audio file with our Universal-3-Pro model and print the transcript text to your terminal.
+This example shows how you can transcribe a pre-recorded audio file with our Universal-3 Pro model and print the transcript text to your terminal.
 
 <Tabs groupId="language">
 <Tab language="python" title="Python" default>
@@ -116,7 +116,7 @@ while (true) {
 
 <Note title="Language support">
 
-Universal-3-Pro supports English, Spanish, Portuguese, French, German, and Italian. To access all 99 languages, use `"speech_models": ["universal-3-pro", "universal-2"]` as shown in the code example. [Read more here.](#99-languages-coverage)
+Universal-3 Pro supports English, Spanish, Portuguese, French, German, and Italian. To access all 99 languages, use `"speech_models": ["universal-3-pro", "universal-2"]` as shown in the code example. [Read more here.](#99-languages-coverage)
 
 </Note>
 
@@ -227,7 +227,7 @@ while (true) {
 
 ## Prompting
 
-Universal-3-Pro delivers great accuracy out of the box. To fine-tune transcription results to your use case, provide a prompt with up to 1,500 words of context in plain language. This helps the model consistently recognize domain-specific terminology, apply your preferred formatting conventions, handle code switching between languages, and better interpret ambiguous speech.
+Universal-3 Pro delivers great accuracy out of the box. To fine-tune transcription results to your use case, provide a prompt with up to 1,500 words of context in plain language. This helps the model consistently recognize domain-specific terminology, apply your preferred formatting conventions, handle code switching between languages, and better interpret ambiguous speech.
 
 ### Verbatim transcription and disfluencies
 
@@ -1364,4 +1364,4 @@ Model routing behavior: The system attempts to use the models in priority order
 
 ## Best practices for prompt engineering
 
-Check out [this guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompt-engineering) to learn even more about how to craft effective prompts for Universal-3-Pro speech transcription, which includes an [AI prompt generator tool](https://www.assemblyai.com/docs/pre-recorded-audio/prompt-engineering#prompt-generator).
+Check out [this guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompt-engineering) to learn even more about how to craft effective prompts for Universal-3 Pro speech transcription, which includes an [AI prompt generator tool](https://www.assemblyai.com/docs/pre-recorded-audio/prompt-engineering#prompt-generator).