{"id":15177168,"url":"https://github.com/intothevoid/rss2podcast","last_synced_at":"2025-10-26T14:31:11.817Z","repository":{"id":226412425,"uuid":"768600553","full_name":"intothevoid/rss2podcast","owner":"intothevoid","description":"Parse, summarise and convert rss feeds into an audio podcast ","archived":false,"fork":false,"pushed_at":"2024-04-07T12:17:00.000Z","size":1180,"stargazers_count":9,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-31T20:22:35.595Z","etag":null,"topics":["ai","coqui","golang","ollama","podcast","rss","tts"],"latest_commit_sha":null,"homepage":"","language":"Go","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/intothevoid.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":"2024-03-07T11:40:17.000Z","updated_at":"2024-12-13T22:46:42.000Z","dependencies_parsed_at":"2024-06-19T16:15:55.871Z","dependency_job_id":"835a4357-bc9d-4372-bdb3-5298c53f3cc6","html_url":"https://github.com/intothevoid/rss2podcast","commit_stats":null,"previous_names":["intothevoid/rss2podcast"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intothevoid%2Frss2podcast","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intothevoid%2Frss2podcast/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intothevoid%2Frss2podcast/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intothevoid%2Frss2podcast/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intothevoid","download_url":"https://codeload.github.com/intothevoid/rss2podcast/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238347634,"owners_count":19456967,"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","coqui","golang","ollama","podcast","rss","tts"],"created_at":"2024-09-27T14:03:32.148Z","updated_at":"2025-10-26T14:31:11.812Z","avatar_url":"https://github.com/intothevoid.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# rss2podcast\n\n\u003cimg src=\"resources/ui.jpg\" width=600px\u003e\u003c/img\u003e\n\nA locally hosted, AI generated podcast from an rss feed. \n\n![workflow](https://github.com/intothevoid/rss2podcast/actions/workflows/go.yml/badge.svg)\n![Go Report Card](https://goreportcard.com/badge/github.com/intothevoid/rss2podcast)\n![GitHub](https://img.shields.io/github/license/intothevoid/rss2podcast)\n![GitHub go.mod Go version](https://img.shields.io/github/go-mod/go-version/intothevoid/rss2podcast)\n![GitHub release (latest by date)](https://img.shields.io/github/v/release/intothevoid/rss2podcast)\n\nPowered by -\n\n\u003cimg src=\"resources/rss.png\" width=80px height=80px\u003e\u003c/img\u003e\n\u003cimg src=\"resources/ollama.png\" width=80px height=80px\u003e\u003c/img\u003e\n\u003cimg src=\"resources/coqui.png\" width=80px height=80px\u003e\u003c/img\u003e\n\u003cimg src=\"resources/kokoro.jpg\" width=80px height=80px\u003e\u003c/img\u003e\n\n## Features\n\n- RSS feed parsing and article extraction\n- Article summarization using Ollama\n- Text-to-speech conversion using multiple engines:\n  - Kokoro TTS (Recommended)\n  - MLX Audio TTS\n  - Coqui TTS\n- Podcast generation with customizable settings\n- Web interface for configuration and control\n\n## Requirements\n\n- Go 1.21 or later\n- Ollama (for article summarization)\n- One of the following TTS engines:\n  - Kokoro TTS (recommended)\n  - MLX Audio TTS\n  - Coqui TTS\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/intothevoid/rss2podcast.git\ncd rss2podcast\n```\n\n2. Install dependencies:\n```bash\ngo mod download\n```\n\n3. Configure the application by editing `config.yaml` or using the web interface.\n\n## Configuration\n\nThe application can be configured using the web interface or by editing the `config.yaml` file. The following settings are available:\n\n### RSS Settings\n- `url`: The RSS feed URL to parse\n- `max_articles`: Maximum number of articles to process\n- `filters`: List of filters to apply to articles\n\n### Ollama Settings\n- `end_point`: The Ollama API endpoint\n- `model`: The Ollama model to use for summarization\n\n### Podcast Settings\n- `subject`: The podcast subject\n- `podcaster`: The podcaster name\n\n### TTS Settings\n- `engine`: The TTS engine to use (\"kokoro\", \"mlx\", or \"coqui\")\n- `kokoro`: Kokoro TTS settings\n  - `url`: The Kokoro TTS API endpoint\n  - `voice`: The voice to use\n  - `speed`: The speech speed (0.25 to 4.0)\n  - `format`: The audio format (mp3, opus, flac, wav, pcm)\n- `mlx`: MLX Audio TTS settings\n  - `url`: The MLX Audio TTS API endpoint\n  - `voice`: The voice to use\n  - `speed`: The speech speed (0.5 to 2.0)\n  - `format`: The audio format (mp3, wav)\n- `coqui`: Coqui TTS settings\n  - `url`: The Coqui TTS API endpoint\n\n## Usage\n\n1. Start the application:\n```bash\ngo run cmd/rss2podcast/main.go\n```\n\n2. Access the web interface at `http://localhost:8080`\n\n3. Configure the application using the web interface or edit `config.yaml`\n\n4. The application will:\n   - Parse the RSS feed\n   - Extract and summarize articles\n   - Convert the summary to audio using the selected TTS engine\n   - Generate a podcast file\n\n## TTS Engines\n\n### Kokoro TTS (Recommended)\nKokoro TTS offers OpenAI-compatible speech synthesis with support for multiple voices and formats. It provides excellent quality with low latency.\n\n### MLX Audio TTS\nMLX Audio TTS is a powerful text-to-speech engine that provides high-quality speech synthesis with support for multiple voices and formats. It offers additional features like direct audio playback and output folder management.\n\n### Coqui TTS\nCoqui TTS provides high-quality speech synthesis with support for multiple voices and formats.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## Acknowledgments\n\n- [Ollama](https://ollama.ai/) for the LLM API\n- [Kokoro TTS](https://github.com/kokoro-tts/kokoro) for the TTS engine\n- [MLX Audio TTS](https://github.com/mlx-audio/mlx-tts) for the TTS engine\n- [Coqui TTS](https://github.com/coqui-ai/TTS) for the TTS engine\n\n## How it works\nThe application reads an rss feed, extracts the articles and summarises them. \n\nRSS + Ollama + TTS = Podcast\n\n### RSS\nThe application reads an rss feed and extracts the articles. Each of these articles are then processed by scraping the article content.\n\n### Ollama\nThe application uses a locally hosted version of Ollama. The Ollama API is used to summarise the article content. Default model used is mistral:7b\n\n### TTS\nThe summarised article content is then converted into an audio podcast using the Coqui TTS API.\n\n## Dependencies\n\nThis project requires the following dependencies to be installed on your system. \n\n### Ollama\n\nYou can install the Ollama server by following the instructions on the [official website](https://ollama.com).\n\nOllama needs to be running on your local machine for the application to work. The application is configured to use the default Ollama server URL `http://localhost:11434/api/generate`. This can be changed via the config.yaml file.\n\n### ffmpeg\n\n`ffmpeg` is a command-line tool for handling multimedia files. It is used to convert the generated audio files to the MP3 format.\n\n#### macOS\n\nYou can use Homebrew to install `ffmpeg` on macOS:\n\n```bash\nbrew install ffmpeg\n```\n\n#### Windows\n\n1. Download the `ffmpeg` build for Windows from the [official website](https://ffmpeg.org/download.html).\n2. Extract the downloaded ZIP file.\n3. Add the `bin` directory from the extracted folder to your system's PATH.\n\n#### Linux\n\nThe installation command depends on your Linux distribution.\n\n##### Ubuntu/Debian\n\n```bash\nsudo apt update\nsudo apt install ffmpeg\n```\n\n### Kokoro TTS (Recommended)\n\nKokoro TTS is a text-to-speech synthesis system that uses deep learning to create human-like speech from text. You can install the Kokoro TTS server by following the instructions on the [official website](https://github.com/nazdridoy/kokoro-tts).\n\n#### Docker:\n  \nCreate a docker-compose.yml file and add the following:\n\n```yaml\nservices:\nkokoro-fastapi-cpu:\n    ports:\n        - 8880:8880\n    image: ghcr.io/remsky/kokoro-fastapi-cpu:latest # or v0.2.3 for last stable version\n```\n\nStart the server by running the following command:\n\n```bash\ndocker compose up -d\n```\n\nThis will start the Kokoro TTS server on port 8880. The server provides a REST API for text-to-speech conversion.\n\n### Coqui TTS\n\nCoqui TTS is a text-to-speech synthesis system that uses deep learning to create human-like speech from text. You can install the Coqui TTS server by following the instructions on the [official website](https://coqui.ai/tts).\n\n#### Docker\n\nStart the container by using the following command:\n\n```bash\ndocker run -d -p 5002:5002 --platform linux/amd64 --entrypoint /usr/local/bin/tts-server ghcr.io/coqui-ai/tts-cpu --model_name tts_models/en/ljspeech/vits\n```\n\n### MLX Audio TTS\n\nMLX Audio TTS is a text-to-speech synthesis system that uses deep learning to create human-like speech from text. You can install the MLX Audio TTS server by following the instructions on the [official website](https://github.com/mlx-audio/mlx-tts).\n\n#### Docker\n\nAs of this writing, MLX Audio TTS needs to be run locally as Docker does not allow GPU access on Apple Silicon.\n\n```bash\n# Install the package\npip install mlx-audio\n\n# Create a virtual environment\npython -m venv venv\n\n# Activate the virtual environment\nsource venv/bin/activate\n\n# Install the dependencies\npip install -r requirements.txt\n\n# Run the server\nmlx_audio.server\n```\nrss2podcast will automatically request the MLX Audio TTS server to generate the audio file.\n\n## Testing\nTo run the tests, use the following command:\n```bash\ngo test ./...\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintothevoid%2Frss2podcast","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintothevoid%2Frss2podcast","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintothevoid%2Frss2podcast/lists"}