{"id":15054659,"url":"https://github.com/skulux/voicetral","last_synced_at":"2026-01-23T22:03:12.130Z","repository":{"id":257626204,"uuid":"858845937","full_name":"Skulux/Voicetral","owner":"Skulux","description":"This repository contains an amateur implementation of an interface between the Ollama model and Applio's TTS and voice conversion services. It serves as a basic example of integrating speech recognition, text generation, and audio processing for personal or experimental use.","archived":false,"fork":false,"pushed_at":"2024-10-06T19:31:56.000Z","size":17,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-30T19:23:02.612Z","etag":null,"topics":["ai","applio","audio-processing","conversational-ai","local","natural-language","ollama","rvc","speech-to-text","stt","text-generation","text-to-speech","tts","voicetral"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Skulux.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":"2024-09-17T16:24:51.000Z","updated_at":"2025-01-20T22:24:22.000Z","dependencies_parsed_at":null,"dependency_job_id":"e38c868d-b730-4589-b900-2c97bd919760","html_url":"https://github.com/Skulux/Voicetral","commit_stats":{"total_commits":11,"total_committers":1,"mean_commits":11.0,"dds":0.0,"last_synced_commit":"75ed168eaca439437516d69d82a3fd2040c74aaf"},"previous_names":["skulux/voicetral"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Skulux%2FVoicetral","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Skulux%2FVoicetral/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Skulux%2FVoicetral/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Skulux%2FVoicetral/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Skulux","download_url":"https://codeload.github.com/Skulux/Voicetral/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251773799,"owners_count":21641698,"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":["ai","applio","audio-processing","conversational-ai","local","natural-language","ollama","rvc","speech-to-text","stt","text-generation","text-to-speech","tts","voicetral"],"created_at":"2024-09-24T21:38:56.185Z","updated_at":"2026-01-23T22:03:12.122Z","avatar_url":"https://github.com/Skulux.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Voicetral\n\n## Overview\n\nThis project provides an interface between the Ollama model and a text-to-speech (TTS) engine using Suno's Bark. It converts user speech input into text, generates responses using Ollama, and then synthesizes and plays back the response using Bark.\n\n## Features\n\n- Speech-to-text conversion using `speech_recognition`.\n- Text generation using the Ollama model.\n- Text-to-speech conversion using Bark.\n- Audio playback using `sounddevice`.\n- Audio resampling and processing with `pydub`.\n\n## Requirements\n\n### Software Dependencies\n\n- Python 3.9\n- [FFmpeg](https://ffmpeg.org/download.html) (for audio processing)\n- **Ollama**: A model service for text generation. [Visit Ollama's website](https://ollama.com) for installation and usage instructions.\n- **Bark**: Used for text-to-speech synthesis.\n\n### Python Packages\n\nThe required Python packages are listed in `requirements.txt`. To install them, use the following command:\n\n    pip install -r requirements.txt\n\n### Configuration\n\n1. **FFmpeg**: Ensure that FFmpeg is installed and accessible in your system's PATH. You can download FFmpeg from [here](https://ffmpeg.org/download.html) and follow the installation instructions for your operating system.\n\n2. **Ollama**: Install and run the Ollama service according to the instructions on their website. Make sure it's accessible at the specified URL.\n\n3. **Bark**: Run the provided `setup_bark.sh` script to download the required models.\n\n4. **Configuration File**: Update the `config.ini` file with the appropriate paths and settings for your environment. \n\n   - `START_PROMPT`: Your initial prompt for the Ollama model.\n   - `OLLAMA_MODEL`: The name of the Ollama model to use.\n   - `BARK_VOICE_PRESET`: Voice preset to use with Bark.\n   - `TTS_OUTPUT_PATH`: Path where the TTS output will be saved.\n\n## Installation\n\n1. Clone the repository:\n    ```bash\n    git clone https://github.com/Skulux/Voicetral\n    cd Voicetral\n    ```\n\n2. Create and activate a virtual environment:\n    ```bash\n    python -m venv venv\n    source venv/bin/activate  # On Windows, use `venv\\Scripts\\activate`\n   ```\n\n3. Install the required packages:\n    ```bash\n    pip install -r requirements.txt\n   ```\n4. Run the Bark setup script to download the models:\n    ```bash\n    ./setup_bark.sh\n    ```\n\n5. Ensure FFmpeg is installed and properly configured in your PATH.\n\n6. Install and start the Ollama service as per its instructions.\n\n## Usage\n\n1. Configure your `config.ini` file with the necessary settings as described in the Configuration section.\n\n2. Run the main script:\n    ```bash\n    python main.py\n    ```\n\n3. Follow the on-screen prompts. Speak into your microphone to interact with the bot.\n\n4. Say \"exit\" to stop the program. It is important if you want to save your conversation history.\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Contributing\n\nFeel free to submit issues or pull requests if you have suggestions or improvements. For significant changes, please open an issue first to discuss what you would like to change.\n\n## Contact\n\nFor questions or feedback, please contact github@petrilionis.lt or open an issue on the project's GitHub repository.\n\n## External Services\n\n- **Ollama**: [Installation and usage instructions](https://ollama.com)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskulux%2Fvoicetral","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fskulux%2Fvoicetral","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskulux%2Fvoicetral/lists"}