From 84e05db366329f721a9f54bf1838b2cbf3adc1fb Mon Sep 17 00:00:00 2001
From: Ben Xu <benx.xu@mail.utoronto.ca>
Date: Mon, 30 Dec 2024 15:11:39 -0500
Subject: [PATCH] add local setup docs

---
 docs/server/configure.mdx | 23 ++++++++++++++++++-----
 docs/server/livekit.mdx   |  8 +++-----
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/docs/server/configure.mdx b/docs/server/configure.mdx
index 6319374..d681b38 100644
--- a/docs/server/configure.mdx
+++ b/docs/server/configure.mdx
@@ -27,7 +27,7 @@ poetry run 01 --profile <profile_name>
 
 `fast.py` uses Cartesia for TTS and Cerebras Llama3.1-8b, which are the fastest providers.
 
-`local.py` uses coqui TTS and runs the --local explorer from Open Interpreter.
+`local.py` requires additional setup to be used with LiveKit. Uses faster-whisper for STT, ollama/codestral for LLM (default), and piper for TTS (default).
 
 ### Custom Profiles
 
@@ -123,11 +123,24 @@ interpreter.local_setup()
 interpreter.tts = "elevenlabs"
 ```
 
-### Local TTS
+### Local TTS and STT with LiveKit
 
-For local TTS, Coqui is used.
+We recommend having Docker installed for the easiest setup. Local TTS and STT relies on the [openedai-speech](https://github.com/matatonic/openedai-speech?tab=readme-ov-file) and [faster-whisper-server](https://github.com/fedirz/faster-whisper-server) repositories respectively. 
 
+#### Local TTS
+1. Clone the [openedai-speech](https://github.com/matatonic/openedai-speech?tab=readme-ov-file) repository
+2. Set `base_url = os.environ.get("OPENAI_BASE_URL", "http://localhost:9000/v1")` to point to localhost at port 9000 in `say.py`
+3. Follow the Docker Image instructions for your system. Default run `docker compose -f docker-compose.min.yml up` in the root. 
+4. Set your profile with local TTS service
 ```python
-# Set your profile with a local TTS service
-interpreter.tts = "coqui"
+interpreter.stt = "local"
+```
+
+#### Local STT
+1. Clone the [faster-whisper-server](https://github.com/fedirz/faster-whisper-server) repository
+2. Follow the Docker Compose Quick Start instructions for your respective system. 
+3. Run `docker run --publish 8001:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER__MODEL=Systran/faster-whisper-small --detach fedirz/faster-whisper-server:latest-cpu` to publish to port 8001 instead of the default 8000 (since our TTS uses this port).
+4. Set your profile with local STT service
+```python
+interpreter.stt = "local"
 ```
\ No newline at end of file
diff --git a/docs/server/livekit.mdx b/docs/server/livekit.mdx
index 2c9d423..7849e36 100644
--- a/docs/server/livekit.mdx
+++ b/docs/server/livekit.mdx
@@ -100,11 +100,9 @@ poetry run 01 --server livekit --expose
 ```
 
 <Note>
-  Currently, our Livekit server only works with Deepgram and Eleven Labs. We are
-  working to introduce all-local functionality as soon as possible. By setting
-  your profile (see [Configure Your Profile](/software/configure)), you can
-  still change your LLM to be a local LLM, but the `interpreter.tts` value will
-  be ignored for the Livekit server.
+  Livekit server now supports Local STT and TTS for fully local pipeline. 
+  Setup instructions are provided in the [configuring your 01](/server/configure#local-tts-and-stt-with-livekit) section.
+
 </Note>
 
 ## Livekit vs. Light Server