{"id":15136500,"url":"https://github.com/barrylee111/voicechat-llm","last_synced_at":"2026-01-19T12:33:53.651Z","repository":{"id":243943202,"uuid":"813838668","full_name":"barrylee111/voicechat-LLM","owner":"barrylee111","description":"A chatbot with both prompt and voicechat capabilities leveraging LangChain, Elasticsearch, and FastAPI. When using voicechat, the user can immerse themselves in the experience by selecting a narrator, like a pirate for instance.","archived":false,"fork":false,"pushed_at":"2024-06-21T21:42:22.000Z","size":201,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-12T08:38:41.043Z","etag":null,"topics":["elasticsearch","fastapi","langchain","largelanguagemodel","python","react","speech-to-text","tailwind","text-to-speech","typescript","websocket","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/barrylee111.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-11T21:01:05.000Z","updated_at":"2024-12-13T10:41:29.000Z","dependencies_parsed_at":"2024-06-22T12:38:39.174Z","dependency_job_id":null,"html_url":"https://github.com/barrylee111/voicechat-LLM","commit_stats":{"total_commits":11,"total_committers":1,"mean_commits":11.0,"dds":0.0,"last_synced_commit":"9c3ac3db78453181b984cb94167fbf8ad8064b6f"},"previous_names":["barrylee111/voicechat-llm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/barrylee111%2Fvoicechat-LLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/barrylee111%2Fvoicechat-LLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/barrylee111%2Fvoicechat-LLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/barrylee111%2Fvoicechat-LLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/barrylee111","download_url":"https://codeload.github.com/barrylee111/voicechat-LLM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247425515,"owners_count":20936968,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["elasticsearch","fastapi","langchain","largelanguagemodel","python","react","speech-to-text","tailwind","text-to-speech","typescript","websocket","whisper"],"created_at":"2024-09-26T06:22:13.480Z","updated_at":"2026-01-19T12:33:53.645Z","avatar_url":"https://github.com/barrylee111.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Overview\n### Demo Link:\nTBD\n\n### VoiceChat\n- Enables user to have a conversation with an LLM (Voice in, Voice out)\n  - Voice input is working, Voice output is currently being constructed\n- Enables user to select a `narrator` that will act according to the description. (The TTS models that will be invoked are part of the next build cycle: AI)\n  - Pirate\n  - Scotsman\n  - More\n\n### TextChat\n  - Enables user to interact with an LLM via prompt\n  - Auto-Complete (part of frontend build cycle) \n\n## Technologies Applied\n### LLM\n- ChatGPT\n\n### Backend Server\n- FastAPI - Text-To-Text and Speech-To-Speech Flows (Next Build Cycle)\n- Django - User creation, authentication, and authorization\n\n### Languages\n- React\n- Typescript\n- Python\n- CSS: Tailwind\n\n### Containerization\n- Docker (Next build cycle)\n\n### Streaming flow of audio input\n- Websockets\n\n### Databases\n- PostGreSQL (User/Auth - Next Build Cycle)\n- VectorDB (Domain specific knowlegdge - RAG architecture)\n\n## Future Planning\n### Conversations\n- User will be able to select any of their previous conversations (limit of X)\n- When selected the convo will populate into the history window above the TextPrompt\n\n### Documents\n- User will be able to upload a doc that will either:\n  - passed in as a one-off for the text or voice-chat prompt\n  - stored permanently as a doc that is referenced when they query the LLM\n\n### User Account Creation and Auth\n- A new service will be constructed in Django to enable noobs to:\n  - Register an account\n  - Log in\n  - Delete the account\n  - Auth for use of LLM\n\n### Clustering\n- EKS / Kubernetes / Terraform\n\n### LLM To SLM\nSwap out ChatGPT for an SLM like Llama3 that is running on our own server.\n\n### Mobile Versions\n- iOS\n- Android","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbarrylee111%2Fvoicechat-llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbarrylee111%2Fvoicechat-llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbarrylee111%2Fvoicechat-llm/lists"}