{"id":47198691,"url":"https://github.com/atomlayer/llama_cute_voice_assistant","last_synced_at":"2026-03-13T12:38:03.923Z","repository":{"id":188565388,"uuid":"678521045","full_name":"atomlayer/llama_cute_voice_assistant","owner":"atomlayer","description":"Llama cute voice assistant","archived":false,"fork":false,"pushed_at":"2023-09-10T21:38:49.000Z","size":587,"stargazers_count":27,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2026-03-06T05:43:00.924Z","etag":null,"topics":["assistant","llama","llama2","oobabooga","rvc","silero","whisper"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/atomlayer.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2023-08-14T18:39:30.000Z","updated_at":"2025-07-20T02:47:41.000Z","dependencies_parsed_at":"2024-08-09T22:10:39.471Z","dependency_job_id":null,"html_url":"https://github.com/atomlayer/llama_cute_voice_assistant","commit_stats":{"total_commits":29,"total_committers":2,"mean_commits":14.5,"dds":0.03448275862068961,"last_synced_commit":"16f20b38b33f4647b414452c4c847575cde216ac"},"previous_names":["atomlayer/llama_cute_voice_assistent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/atomlayer/llama_cute_voice_assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomlayer%2Fllama_cute_voice_assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomlayer%2Fllama_cute_voice_assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomlayer%2Fllama_cute_voice_assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomlayer%2Fllama_cute_voice_assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atomlayer","download_url":"https://codeload.github.com/atomlayer/llama_cute_voice_assistant/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomlayer%2Fllama_cute_voice_assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30467555,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-13T11:00:43.441Z","status":"ssl_error","status_checked_at":"2026-03-13T11:00:23.173Z","response_time":60,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["assistant","llama","llama2","oobabooga","rvc","silero","whisper"],"created_at":"2026-03-13T12:38:03.259Z","updated_at":"2026-03-13T12:38:03.904Z","avatar_url":"https://github.com/atomlayer.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# llama_cute_voice_assistant\r\n\r\nMotivation: Many voice assistants with artificial intelligence have an unpleasant voice. While it may be a matter of personal preference. I aim to create a more human assistant that allows you to plug in cute anime character voices and vtuber voices.\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\nSolution diagram:\r\n\r\n![](media/2858db90ced343578868eeafaf30ee79.png)\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n# How to install\r\n\r\n*This guide may not be the most detailed. It will need to be improved.*\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\r\n## Step 1 - Install llama_cute_voice_assistant\r\n\r\n*Installation procedure for Windows*\r\n\r\n1) Install git https://git-scm.com/downloads\r\n2) Install cudatoolkit (You should only choose versions of cuda that pytorch supports. See supported versions here https://pytorch.org/get-started/locally/) \r\n3) Install miniconda https://docs.conda.io/en/latest/miniconda.html\r\n4) Open miniconda console\r\n5) Create new conda environment\r\n\r\n```\r\nconda create --name llama_cute_voice_assistant python=3.11\r\n```\r\n\r\n6) Activate conda environment\r\n\r\n```\r\nconda activate llama_cute_voice_assistant\r\n```\r\n\r\n7) Clone project\r\n\r\n```\r\ngit clone https://github.com/atomlayer/llama_cute_voice_assistant.git\r\n```\r\n\r\n8) Go to project directory\r\n\r\n```\r\ncd llama_cute_voice_assistant\r\n```\r\n\r\n\r\n9) Install pytorch \r\n- Go to https://pytorch.org/get-started/locally/\r\n- Generate a command to install pytorch for your system (the command will be like this: pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 )\r\n- Execute the command\r\n\r\n10) Install the libraries\r\n\r\n```\r\npip install SpeechRecognition==3.10.0 \r\npip install pyttsx3==2.90 \r\npip install soundfile==0.12.1\r\npip install simpleaudio==1.0.4\r\npip install pygame==2.5.1\r\nconda install PyAudio\r\npip install openai-whisper --no-cache-dir\r\npip install omegaconf==2.3.0\r\npip install git+https://github.com/openai/whisper.git\r\nconda install -c conda-forge ffmpeg\r\n```\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\r\n\r\n## Step 2 - Install oobabooga Text generation web UI\r\n\r\n1) [https://github.com/oobabooga/text-generation-webui\\#one-click-installers](https://github.com/oobabooga/text-generation-webui#one-click-installers)\r\n\r\n2) Open the oobabooga Text Generation web UI using the **-api** parameter.\r\n\r\n3) On the model tab: download and run your favorite AI model.\r\n\r\n4) On the Chat settings \\\u003e Character tab: set your character name and description.\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\r\n## Step 3 - Install Realtime Voice Changer\r\n\r\nDetailed instruction - \u003chttps://www.youtube.com/watch?v=_JXbvSTGPoo\u003e\r\n\u003cbr\u003e\r\n\r\n1) Download https://huggingface.co/wok000/vcclient000/blob/main/MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.11.zip\r\n\r\n2) Unpack the archive\r\n\r\n3) Run start_http.bat\r\n\r\n4) Join the AI Hub Discord: https://discord.gg/aihub\r\n\r\n5) Go to the search-models channel\r\n\r\n6) Find and download the model you like\r\n\r\n7) Click the edit button in the Realtime Voice Changer Client\r\n\r\n8) Upload the model to a free cell\r\n\r\n9) Adjust the best TUNE parameter for your voice.\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\r\n## Step 4 – Install the virtual microphone\r\n\r\n1) Download and install VB-CABLE Virtual Audio Device \u003chttps://vb-audio.com/Cable/\u003e\r\n\r\n2) Open Realtime Voice Changer\r\n\r\n3) Set up an audio input: Cable Output (VB-Audio Virtual Cable)\r\n\r\n![](media/6b7f24ec79fe7fb7ab599c5ee15e1a88.png)\r\n\r\n4) Press start button\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\r\n\r\n## Step 5 - Change the settings in the settings.py file\r\n\r\n1) Replace oobabooga_api_name and wake words.\u003cbr\u003e\r\n   oobabooga_api_name - the name of one of your characters in oobabooga text generation web UI (Paremeters \u003e Character tab)\r\n```\r\noobabooga_api_name = \"Lisa\"\r\nwake_words = [\"lisa\"]\r\n```\r\n\r\n\u003cbr\u003e\r\n\u003cbr\u003e\r\n\r\n# How to use\r\n\r\n1) Open conda console in the project folder\r\n2) Run the command: \r\n```\r\npython voice_chat.py\r\n```\r\n3) Say the wake word and the command for your assistant.\r\n\r\n\r\n# Links\r\nhttps://github.com/davabase/whisper_real_time\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatomlayer%2Fllama_cute_voice_assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatomlayer%2Fllama_cute_voice_assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatomlayer%2Fllama_cute_voice_assistant/lists"}