Explore Docs API Blog Pricing Contact Sign In

Richard Stallbot

💬 Agent

Meet Richard Stallbot, who really thinks he is Richard Stallman. He has strong opinions about those who are not working on free and libre software. Ask him about Apple and ChatGPT! He's a Gooey.AI RAG bot, using Stallman's writings, LLAMA3 70b as the LLM, 11labs for the voice and wav2lip as the lipsync engine. Please fork and make your own!

2y ago

Instructions

Prompt Library

Language Model

Knowledge Base

Show as Links

💪 Capabilities

🦻 Speech Recognition & Translation

🗣️ Text to Speech & Lipsync

Text-to-Speech Provider

Note: You need to be Signed In to use ElevenLabs voices.

Voice

Model

🫦 Add Lipsync Video

👩‍🦰 Input Face

Upload a video/image with one human face. mp4, mov, png, jpg or gif preferred.

Lipsync Model

🩻 Photo & Document Intelligence

📊 Analytics & Evaluation

🛠️ Developer Tools and Functions

Variables

platform

string

⚙️ Settings

Stability

A lower stability provides a broader emotional range.
A value lower than 0.3 can lead to too much instability.
Read more.

Similarity Boost

Dictates how hard the model should try to replicate the original voice.
Read more.

Eleven Labs Supported Languages

With Multilingual V2 voice model

English, Japanese, Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian, Russian

⌖ Lipsync Face Padding

Adjust the detected face bounding box. Often leads to improved results. Recommended to give at least 10 padding for the chin region.

Head

Chin

Left Cheek

Right Cheek

📄 Knowledge Base

👩‍🏫 Search Instructions

Citation Style

🔗 Shorten citation links

Cache

By default we embed your knowledge files & links and cache their contents for fast responses.

Always Check for Updates

Create Synthetic Data

To improve answer quality, pick a synthetic data maker workflow to scan & OCR any images in your documents or transcribe & translate any videos. It also can synthesize a helpful FAQ. Adds ~2 minutes of one-time processing per file.

Advanced Settings

In general, you should not need to adjust these.

👁‍🗨 Conversation Summarization

These instructions run before the knowledge base is search and should reduce the conversation into a search query most relevant to the user's last message.

🔑 Keyword Extraction

Instructions to create a query for keyword/hybrid BM25 search. Runs after the Conversations Summarization above and can use its result via {{ final_search_query }}.

✏ Embeddings Model

Dense Embeddings Weightage

Weightage for dense vs sparse embeddings. 0 for sparse, 1 for dense, 0.5 for equal weight.
Generally speaking, dense embeddings excel at understanding the context of the query, whereas sparse vectors excel at keyword matches.

Max Citations

The maximum number of document search citations.

Max Snippet Words

After a document search, relevant snippets of your documents are returned as results.
This setting adjusts the maximum number of words in each snippet (tokens = words * 2).
A high snippet size allows the LLM to access more information from your document results, at the cost of being verbose and potentially exhausting input tokens (which can cause a failure of the copilot to respond).

Snippet Overlap Ratio

Your knowledge base documents are split into overlapping snippets.
This settings adjusts how much those snippets overlap (overlap tokens = snippet tokens / overlap ratio).
In general you shouldn't need to adjust this.

🔠 Language Model Settings

Avoid Repetition

Response Format

Max Output Tokens

Creativity (aka Sampling Temperature)

Answer Outputs

Run cost = 11 credits

Breakdown: 2 (Llama 3 70B • Meta AI [Redirects to Llama 4 Maverick]) + 3/run + 4 credits per 10 words (11labs) + 1 (lipsync)

With each run, you agree to Gooey.AI's terms & privacy policy.

🐞 Debug

How to Use This Recipe

🙋🏽‍♀️ Need more help? Join our Discord