{"id":24987661,"url":"https://github.com/bharath-tars/speech-to-speech-bot","last_synced_at":"2026-05-04T02:31:55.429Z","repository":{"id":273039841,"uuid":"918530863","full_name":"Bharath-tars/Speech-to-Speech-Bot","owner":"Bharath-tars","description":"A real-time voice bot using LLaMA 3.3-80B for intelligent responses, OpenAI Whisper V3 Turbo for speech-to-text, and gTTS for text-to-speech conversion.","archived":false,"fork":false,"pushed_at":"2025-01-22T11:44:19.000Z","size":20,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-29T11:16:48.896Z","etag":null,"topics":["gtts","huggingface","llama-3-70b","python","speech-to-speech","streamlit","tranformers","whisper-ai"],"latest_commit_sha":null,"homepage":"https://huggingface.co/spaces/BharathTars/Nova-Voice-BOT","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Bharath-tars.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":"2025-01-18T06:55:44.000Z","updated_at":"2025-01-22T11:44:23.000Z","dependencies_parsed_at":"2025-01-18T08:27:50.810Z","dependency_job_id":"2c0333a6-7fc2-4c01-a9cb-3c04c6b1cdb9","html_url":"https://github.com/Bharath-tars/Speech-to-Speech-Bot","commit_stats":null,"previous_names":["bharath-tars/speech-to-speech-bot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Bharath-tars/Speech-to-Speech-Bot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FSpeech-to-Speech-Bot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FSpeech-to-Speech-Bot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FSpeech-to-Speech-Bot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FSpeech-to-Speech-Bot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Bharath-tars","download_url":"https://codeload.github.com/Bharath-tars/Speech-to-Speech-Bot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FSpeech-to-Speech-Bot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32592354,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"online","status_checked_at":"2026-05-04T02:00:06.625Z","response_time":58,"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":["gtts","huggingface","llama-3-70b","python","speech-to-speech","streamlit","tranformers","whisper-ai"],"created_at":"2025-02-04T11:48:32.476Z","updated_at":"2026-05-04T02:31:55.410Z","avatar_url":"https://github.com/Bharath-tars.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Speech-to-Speech Conversational Bot\n\n## Introduction\nThe **Speech-to-Speech Conversational Bot** is a real-time voice interaction system that combines cutting-edge technologies to enable seamless, intuitive conversations. It utilizes advanced language models and speech processing tools to provide a natural and engaging user experience. \n\n## Features\n- **Speech Input**: Records user audio through the interface.\n- **Real-time Transcription**: Converts speech to text using **OpenAI Whisper V3 Turbo** via Groq's inference client.\n- **Intelligent Responses**: Generates context-aware responses using **LLaMA 3.3-80B**.\n- **Speech Output**: Converts responses back to speech using **gTTS** for natural voice playback.\n- **User Interface**: Built with **Streamlit** for easy interaction and audio visualization.\n\n## Stack Design\n- **Frontend**: Streamlit for audio recording and response display.\n- **Speech-to-Text**: OpenAI Whisper V3 Turbo accessed through Groq's inference client.\n- **Language Model**: LLaMA 3.3-80B for generating intelligent and conversational responses.\n- **Text-to-Speech**: gTTS for converting text back to speech.\n\n## Workflow\n1. **Audio Recording**: The user records their query using the Streamlit interface.\n2. **Speech Transcription**: The recorded audio is sent to the **Whisper V3 Turbo** model via Groq's inference client for transcription.\n3. **Response Generation**: The transcribed text is passed to the **LLaMA 3.3-80B** model to generate a contextually appropriate response.\n4. **Speech Synthesis**: The generated response is converted back into speech using **gTTS**.\n5. **Playback**: The audio response is played back to the user through the interface.\n\n## Installation\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/your-username/speech-to-speech-bot.git\n   cd speech-to-speech-bot\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbharath-tars%2Fspeech-to-speech-bot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbharath-tars%2Fspeech-to-speech-bot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbharath-tars%2Fspeech-to-speech-bot/lists"}