{"id":20574793,"url":"https://github.com/scf4/llmvoicepoc","last_synced_at":"2026-04-21T14:03:27.659Z","repository":{"id":255663109,"uuid":"841864798","full_name":"scf4/llmvoicepoc","owner":"scf4","description":"Proof of concept, see README.md","archived":false,"fork":false,"pushed_at":"2024-12-18T04:39:04.000Z","size":29,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-16T21:40:41.650Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://scottinallca.ps","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/scf4.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":"2024-08-13T07:42:25.000Z","updated_at":"2024-12-18T04:39:07.000Z","dependencies_parsed_at":"2024-09-06T16:17:13.352Z","dependency_job_id":"0ccc555b-fa1b-47a8-9247-53c2440733c2","html_url":"https://github.com/scf4/llmvoicepoc","commit_stats":null,"previous_names":["scf4/shapevoice","scf4/llmvoicepoc"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scf4%2Fllmvoicepoc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scf4%2Fllmvoicepoc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scf4%2Fllmvoicepoc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/scf4%2Fllmvoicepoc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/scf4","download_url":"https://codeload.github.com/scf4/llmvoicepoc/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242196108,"owners_count":20087762,"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":[],"created_at":"2024-11-16T05:37:07.986Z","updated_at":"2026-04-21T14:03:27.616Z","avatar_url":"https://github.com/scf4.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Whisper/LLM Voice Chat\nA quick/messy proof of concept as an attempt at a low-latency, natural-feeling (and interruptible) voice-to-voice chat using LLMs.\n\n## How to run\n1. Clone the repo `https://github.com/scf4/shapevoice.git`\n2. Install required packages `pip install -r requirements.txt`\n3. Rename `.env.example` to `.env` and add your [Cartesia](https://cartesia.ai) and [Groq](https://groq.com) API keys.\n4. Run `main.py`\n5. **Wear headphones** (see below for limitations)\n\n\u003e **Note:** You will likely need to adjust some of the constants such as silence threshold etc.\n\n## Recommended next steps\n- [ ] Improve voice activity detection (VAD). Currently, it's very sensitive to background noise which Whisper infers as phrases such as \"Thank you\" or \"Thanks for watching\", etc. \n- [ ] Echo cancellation to prevent the assistant from hearing itself and responding. \n- [ ] Stream LLM output to TTS\n- [ ] When the user interrupts, replace the assistant's response in the message history with a cut-off version at the same point\n- [ ] Don't queue up multiple user messages/responses at once. Replace with messages concatenated into a single message.\n- [ ] Remove noise from the audio input, adjust thresholds based on user automatically etc.\n- [ ] General refactor/cleanup\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscf4%2Fllmvoicepoc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fscf4%2Fllmvoicepoc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fscf4%2Fllmvoicepoc/lists"}