{"id":31366432,"url":"https://github.com/makelinux/speaking-llm","last_synced_at":"2025-09-27T10:58:33.078Z","repository":{"id":315892333,"uuid":"1061142075","full_name":"makelinux/speaking-llm","owner":"makelinux","description":"Speech recognition and text-to-speech for Llama Stack, for Linux only","archived":false,"fork":false,"pushed_at":"2025-09-21T11:50:13.000Z","size":9,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-21T13:23:13.090Z","etag":null,"topics":[],"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/makelinux.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-21T10:29:20.000Z","updated_at":"2025-09-21T11:50:16.000Z","dependencies_parsed_at":"2025-09-21T17:31:16.632Z","dependency_job_id":null,"html_url":"https://github.com/makelinux/speaking-llm","commit_stats":null,"previous_names":["makelinux/speaking-llm"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/makelinux/speaking-llm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/makelinux%2Fspeaking-llm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/makelinux%2Fspeaking-llm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/makelinux%2Fspeaking-llm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/makelinux%2Fspeaking-llm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/makelinux","download_url":"https://codeload.github.com/makelinux/speaking-llm/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/makelinux%2Fspeaking-llm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":277219228,"owners_count":25781447,"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","status":"online","status_checked_at":"2025-09-27T02:00:08.978Z","response_time":73,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2025-09-27T10:58:28.443Z","updated_at":"2025-09-27T10:58:33.073Z","avatar_url":"https://github.com/makelinux.png","language":"Python","readme":"# Speaking LLM\n\nA voice-enabled AI assistant that combines speech recognition, text-to-speech, and LLM processing using Llama Stack.\n\n## Features\n\n- **Voice Input**: Real-time speech recognition using Google Speech Recognition\n- **Voice Output**: Text-to-speech synthesis using gTTS\n- **LLM Integration**: Powered by Llama Stack with configurable models\n\n## Requirements\n\n- **Linux operating system** (tested on Fedora, may work on other distributions)\n- Python 3.10+\n- Microphone and speakers/headphones\n- Internet connection (for Google Speech Recognition and gTTS)\n- Llama Stack server\n\n## Installation\n\n### Standard Installation\n\n```bash\npip install .\n```\n\n### Development Installation\n\n```bash\npip install -e .\n```\n\nAfter installation, you can run the application from anywhere:\n\n```bash\nspeaking-llm --help\n```\n\n## Usage\n\n### Basic Voice Assistant\n\n```bash\nspeaking-llm\n```\n\nOr if running from source:\n\n```bash\npython -m speaking_llm.speaking_llm\n```\n\n## Configuration\n\nEdit an optional `agent_config.yaml` file to customize the agent:\n\n```yaml\nagent_config:\n  model: llama3.2:3b\n  toolgroups:\n    - mymcp\n    - name: builtin::rag/knowledge_search\n      args:\n        vector_db_ids:\n          - your-vector-db-id\n  sampling_params:\n    strategy:\n      type: top_p\n      temperature: 1e-9\n      top_p: 0\n```\n\nEnvironment variables in config are expanded using `${VAR_NAME}` syntax.\n\n## Architecture\n\n```\nMicrophone → Speech Recognition → Llama Stack → Text-to-Speech → Speakers\n```\n\n### Components\n\n- **Speech Input**: Google Speech Recognition API\n- **LLM Backend**: Llama Stack\n- **Speech Output**: gTTS (Google Text-to-Speech)\n\n## Voice Commands\n\n- Say **\"quit\"**, **\"exit\"**, **\"stop\"**, **\"goodbye\"**, **\"bye\"**, or **\"thank you\"** to end the session\n- Speak naturally - the assistant will process your request and respond with voice\n\n## Files\n\n- `speaking_llm/speaking_llm.py` - Main application\n- `speaking_llm/speech_output.py` - Text-to-speech functionality\n- `agent_config.yaml` - Optional agent configuration\n\n## Troubleshooting\n\n### Audio Issues\n\n1. **No microphone found**\n   - Check microphone permissions\n   - Ensure PulseAudio is running: `pulseaudio --check`\n   - List audio devices: `pactl list sources short`\n\n2. **Speech recognition errors**\n   - Check internet connection\n   - Verify microphone is working: `arecord -d 5 test.wav \u0026\u0026 play -q -v 0.1 test.wav`\n\n3. **Text-to-speech not working**\n   - Check internet connection\n   - Verify gTTS: `gtts-cli hi | play -q -v 0.1 -t mp3 -`\n\n## Development\n\nRun linting:\n```bash\n./lint.sh\n```\n\nTest echo mode:\n```bash\nspeaking-llm --echo\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmakelinux%2Fspeaking-llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmakelinux%2Fspeaking-llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmakelinux%2Fspeaking-llm/lists"}