{"id":"speaches","name":"Speaches","maker":"Speaches contributors","url":"https://github.com/speaches-ai/speaches","repo":"speaches-ai/speaches","summary":"An OpenAI-API-compatible server for speech-to-text and text-to-speech that runs locally.","details":"Serves transcription and synthesis models through endpoints that follow the OpenAI audio API, so existing clients can point at it. It also supports a realtime endpoint. The code is MIT licensed.","open_source":true,"hosted":false,"speaks":["openai-api"],"also":["runtimes"],"verified":"2026-11-15","category":"voice","category_name":"Voice agents and realtime speech","page":"https://modelmoot.com/tools/speaches","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}