diff --git a/README.md b/README.md
index 11711a6..441a65c 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 ![AI_ENV](logo.webp)
 
-Unlock the power of AI—right from your Linux terminal.
+Unlock the power of AI right from your Linux terminal.
 
 This project delivers a fully local AI environment, running open source language models directly on your machine. 
 
@@ -11,8 +11,8 @@ No cloud. No GAFAM. Just full privacy, control, and the freedom to manipulate co
 ## How it works
 
 * [Ollama](https://ollama.com/) run language models on the local machine.
-* [openedai-speech](https://github.com/matatonic/openedai-speech) provides text-to-speech capability.
-* [nginx](https://nginx.org/en/) add an authentication to the API.
+* [speaches.ai](https://speaches.ai) provides text-to-speech capability.
+* [nginx](https://nginx.org/en/) adds an authentication to the API.
 * [AIChat](https://github.com/sigoden/aichat) is used as LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents.
 
 Everything is free, open-source, and automated using Docker Compose and shell scripts. 
@@ -23,11 +23,7 @@ It doesn't require an internet connection to work once the models have been down
 
 To run this project efficiently, a powerful computer with a recent NVIDIA GPU is required.
 
-As an example, I achieved good performance with an Intel(R) Core(TM) i7-14700HX, a GeForce RTX 4050 (6GB VRAM), and 32GB of RAM using the [qwen2.5:7b](https://ollama.com/library/qwen2.5) model.
-
-The model [qwen2.5-coder:32b](https://ollama.com/library/qwen2.5-coder:32b) is usable but slow with this configuration.
-
-Note that more modest models like [llama3.2:3b](https://ollama.com/library/llama3.2) require much fewer resources and still allow you to do a lot of things.
+As an example, I achieved good performance with an Intel(R) Core(TM) i7-14700HX, a GeForce RTX 4050 (6GB VRAM), and 32GB of RAM using the [gemma3:12b-it-qat](https://ollama.com/library/gemma3:12b-it-qat) model.
 
 On GNU/Linux, you must use the [NVIDIA Container Toolkit](https://github.com/NVIDIA/nvidia-container-toolkit).
 
@@ -35,22 +31,22 @@ Note that it is probably possible to run the project on other GPUs or modern Mac
 
 ## How to launch the server
 
-Choose the models you wish to use in the docker-compose.yaml file.
+Choose the models you wish to use in the `docker-compose.yaml` file.
 
-```
+```bash
 environment:
-      - MODELS=....
+      - MODELS=...
 ```
 
 Add an API key to secure server access by adding a `.env` file like this:
 
-```
+```bash
 LLM_API_KEY=1234567890
 ```
 
 Create a user authentication for aichat Web UI:
 
-```
+```bash
 htpasswd -c src/nginx/htpasswd user
 ```
 
@@ -61,13 +57,13 @@ docker compose up --build -d
 ```
 
 Then wait for the models to finish downloading using the following command to display the status:
-```
+```bash
 docker-compose logs -f ollama_provision
 ```
 
 ## How to use
 
-The `setup_desktop.sh` script allows for copying a compiled static version of [AIChat](https://github.com/sigoden/aichat) from a container to your host and configuring the tool.
+The `setup_desktop.sh` script allows you to copy a compiled static version of [AIChat](https://github.com/sigoden/aichat) from a container to your host and configure the tool.
 
 ### AIChat essentials
 
@@ -77,8 +73,8 @@ aichat "10 fictitious identities with username, firstname, lastname and email th
 ```
 
 Request a snippet of code:
-```
-aichat -m ollama:qwen2.5-coder:32b -c "if a docker image exist in bash"
+```bash
+aichat -m ollama:gemma3:12b-it-qat -c "if condition to check if a docker image exist in bash"
 ```
 
 To launch a chatbot while maintaining context:
@@ -86,13 +82,13 @@ To launch a chatbot while maintaining context:
 aichat -s
 ```
 
-Pipe a command and interpret the result:
-```
-ps aux | aichat 'which process use the most memory'
+Using shell pipe:
+```bash
+cat README.md | aichat -m ollama:llama3.1:8b 'Check the spelling, grammar, and phrasing. Anwser the correction using diff format'
 ```
 
 Using roles:
-```
+```bash
 aichat -r short "tcp port of mysql"
 ./tools/speech.sh synthesize --play --lang en --voice bryce "$(aichat -r english-translator 'Bienvenue dans le monde de l AI et de la ligne de commande.')"
 ```
@@ -103,13 +99,13 @@ Go to the [AIChat](https://github.com/sigoden/aichat) website for other possible
 
 For this features, use the speech.sh script like this:
 
-```
-./speech.sh synthesize --play --lang fr --voice pierre "Bonjour, aujourd'hui nous somme le $(date +%A\ %d\ %B\ %Y)."
+```bash
+./tools/speech.sh synthesize --play --lang fr --voice pierre "Bonjour, aujourd'hui nous somme le $(date +%A\ %d\ %B\ %Y)."
 ```
 
 ## How to Use Remotely
 
-The API authentication via Nginx allows you to open the API on the internet and use it remotely.
+The API authentication via Nginx allows you to open the API on the internet and use it remoteli.
 
 By adding a reverse proxy like Caddy in front of it, you can also add TLS encryption. 
 
@@ -118,7 +114,7 @@ This way, you can securely use this environment remotely.
 To use script tools in a remote context, use the environment variables TTS_API_HOST and modify AIChat config (~/.config/aichat/config.yaml) .
 
 Example:
-```
+```bash
 export TTS_API_HOST="https://your-remote-domain"
 ./tools/speech.sh ... 
 ```