refine model descriptions for clarity and consistency

intro.md

@@ -1,11 +1,10 @@
+Welcome! This interactive demo lets you denoise and enhance speech using **ai-coustics models**. Choose from three options, each designed for different use cases:  
 
-Welcome! This interactive demo lets you denoise and enhance audio files using ai-coustics models. Choose from three models, each designed for specific use cases:
+- [**Quail**](https://ai-coustics.com/2025/07/02/meet-quail-the-most-advanced-real-time-speech-enhancement-model/): Our lightest model, created for real-time voice isolation. Try it for free or integrate via our [SDK](https://docs.ai-coustics.com/sdk/overview).  
+- [**Finch**](https://ai-coustics.com/2025/06/12/introducing-finch-2-the-new-aicoustics-model-for-studio-quality-speech/): A larger, subtractive model focused on voice isolation and noise removal while preserving the original voice.
+- [**Lark**](https://ai-coustics.com/2025/07/29/lark-2-next-generation-reconstructive-speech-enhancement/): Our most advanced, generative model for universal speech enhancement. Lark not only removes noise but also reconstructs and restores lost details in audio, keeping the speaker’s voice intact.
 
-- [Quail](https://ai-coustics.com/2025/07/02/meet-quail-the-most-advanced-real-time-speech-enhancement-model/): Our smallest, most lightweight model for real-time voice isolation. Try it for free here or integrate it with our [SDK](https://docs.ai-coustics.com/sdk/overview).
-- [Finch](https://ai-coustics.com/2025/06/12/introducing-finch-2-the-new-aicoustics-model-for-studio-quality-speech/): A larger, subtractive model focused on voice isolation and noise removal. Finch removes only unwanted parts of the signal, preserving the original speech. Access it via our [API](https://docs.ai-coustics.com/api-reference/quickstart).
-- [Lark](https://ai-coustics.com/2025/07/29/lark-2-next-generation-reconstructive-speech-enhancement/): Our most advanced, generative model for universal speech enhancement. Lark not only removes noise but also reconstructs and restores lost details in audio, keeping the speaker’s voice intact. Also available through our [API](https://docs.ai-coustics.com/api-reference/quickstart).
-
-**How to Use**
-
-Upload or record a noisy speech sample to enhance its quality. You can also add background noise and adjust the enhancement level to your preference. Quail is free to use here; for Finch and Lark, obtain an API key from our website (includes a 120-minute free trial). Explore preprocessed examples below to preview the capabilities of each model.
+Finch and Lark are available via our [API](https://docs.ai-coustics.com/api-reference/v2/upload-media-file). To get started, request an [API key](https://ai-coustics.com/api/). You’ll receive 120 minutes for free. For additional usage, see our [pricing details](https://ai-coustics.com/pricing/).
 
+**How to use**  
+Upload or record a noisy audio sample, optionally add background noise, and adjust the enhancement level to your preference. Select the model you want to use. Note that Quail is typically the fastest option. You can also try the example clips below to explore to preview the capabilities of each model.

model_info.md

@@ -1,3 +1,3 @@
- [QUAIL](https://ai-coustics.com/2025/07/02/meet-quail-the-most-advanced-real-time-speech-enhancement-model/): lightweight, real-time voice isolation (no API key needed).
+ [QUAIL](https://ai-coustics.com/2025/07/02/meet-quail-the-most-advanced-real-time-speech-enhancement-model/): lightweight, fast voice isolation (no API key needed)
  [FINCH](https://ai-coustics.com/2025/06/12/introducing-finch-2-the-new-aicoustics-model-for-studio-quality-speech/): advanced voice isolation (API key required).
 [LARK 2](https://ai-coustics.com/2025/07/29/lark-2-next-generation-reconstructive-speech-enhancement/): universal speech enhancement model (API key required).