[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72311":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":8,"language":10,"languages":8,"totalLinesOfCode":8,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":8,"rankLanguage":8,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":24,"topics":25,"createdAt":8,"pushedAt":8,"updatedAt":35,"readmeContent":36,"aiSummary":37,"trendingCount":15,"starSnapshotCount":15,"syncStatus":38,"lastSyncTime":39,"discoverSource":40},72311,"speaches","speaches-ai\u002Fspeaches","speaches-ai",null,"https:\u002F\u002Fspeaches.ai\u002F","Python",3377,401,30,108,0,11,34,99,33,103.71,"MIT License",false,"master",true,[26,27,28,29,30,31,32,33,34],"docker","docker-compose","faster-whisper","openai-api","openai-whisper","openai-whisper-translation","transcription","whisper","whisper-ai","2026-06-12 04:01:04","# Speaches\n\n`speaches` is an OpenAI API-compatible server supporting streaming transcription, translation, and speech generation. Speach-to-Text is powered by [faster-whisper](https:\u002F\u002Fgithub.com\u002FSYSTRAN\u002Ffaster-whisper) and for Text-to-Speech [piper](https:\u002F\u002Fgithub.com\u002Frhasspy\u002Fpiper) and [Kokoro](https:\u002F\u002Fhuggingface.co\u002Fhexgrad\u002FKokoro-82M) are used. This project aims to be Ollama, but for TTS\u002FSTT models.\n\nSee the documentation for installation instructions and usage: [speaches.ai](https:\u002F\u002Fspeaches.ai\u002F)\n\n## Features:\n\n- OpenAI API compatible. All tools and SDKs that work with OpenAI's API should work with `speaches`.\n- Audio generation (chat completions endpoint) | [OpenAI Documentation](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Frealtime)\n  - Generate a spoken audio summary of a body of text (text in, audio out)\n  - Perform sentiment analysis on a recording (audio in, text out)\n  - Async speech to speech interactions with a model (audio in, audio out)\n- Streaming support (transcription is sent via SSE as the audio is transcribed. You don't need to wait for the audio to fully be transcribed before receiving it).\n- Dynamic model loading \u002F offloading. Just specify which model you want to use in the request and it will be loaded automatically. It will then be unloaded after a period of inactivity.\n- Text-to-Speech via `kokoro`(Ranked #1 in the [TTS Arena](https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FPendrokar\u002FTTS-Spaces-Arena)) and `piper` models.\n- GPU and CPU support.\n- [Deployable via Docker Compose \u002F Docker](https:\u002F\u002Fspeaches.ai\u002Finstallation\u002F)\n- [Realtime API](https:\u002F\u002Fspeaches.ai\u002Fusage\u002Frealtime-api)\n- [Highly configurable](https:\u002F\u002Fspeaches.ai\u002Fconfiguration\u002F)\n\nPlease create an issue if you find a bug, have a question, or a feature suggestion.\n\n## Demos\n\n### Realtime API\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F457a736d-4c29-4b43-984b-05cc4d9995bc\n\n(Excuse the breathing lol. Didn't have enough time to record a better demo)\n\n### Streaming Transcription\n\nTODO\n\n### Speech Generation\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F0021acd9-f480-4bc3-904d-831f54c4d45b\n","Speaches 是一个兼容OpenAI API的服务器，支持流式转录、翻译和语音生成。其核心功能包括基于faster-whisper的语音到文本转换以及使用piper和Kokoro模型的文本到语音转换。该项目具备实时API支持、动态模型加载\u002F卸载能力，并且支持GPU和CPU运行环境。此外，它还提供了通过Docker Compose或Docker进行部署的能力，使得配置和使用变得更加灵活便捷。Speaches适用于需要高质量语音识别与合成服务的应用场景，如智能助手、客户服务系统或任何需要将文字信息转化为语音输出的场合。",2,"2026-06-11 03:41:18","high_star"]