Speaches
OpenAI-compatible speech-to-text and text-to-speech server (faster-whisper, Kokoro, Piper).
Quick answer
Speaches is an openAI-compatible speech-to-text and text-to-speech server (faster-whisper, Kokoro, Piper), listed under Speech & translation. A typical small-business use: transcribe meeting or call recordings without a cloud speech API. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: MIT, which allows internal business use. Activity is low: the last commit was on Apr 18, 2026.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 22, 2026.
What is Speaches?
Speaches is an OpenAI-API-compatible server for transcription, translation and speech synthesis. It supports streaming transcription, a realtime API and dynamic model loading, and runs on CPU or CUDA GPUs.
Where it fits in a 10–200 person business
- Transcribe meeting or call recordings without a cloud speech API
- Add voice input/output to an internal assistant through the OpenAI audio API
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Speaches? (license)
| License | MIT |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed. Speech models keep their own licenses. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
What hardware does Speaches need?
The project does not publish a minimum CPU/RAM figure, so we leave it blank rather than guess.
GPU: Optional (CUDA image). A CPU image is available.
No official RAM figures.
Source: speaches.ai/installation/
How much does it cost to host Speaches per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy Speaches
Method: Docker
docker run --rm --detach --publish 8000:8000 --name speaches \
--volume hf-hub-cache:/home/ubuntu/.cache/huggingface/hub \
ghcr.io/speaches-ai/speaches:latest-cpuFrom the official instructions: speaches.ai/installation/. Always check the source for the current version before you run it.
Known gotchas when self-hosting Speaches
- Separate images and Compose files exist for CPU, CUDA and CUDA with CDI. Pick the one matching your host, or GPU acceleration will not be used. source
Alternatives in Speech & translation
- LibreTranslate Self-hosted machine translation API with no dependency on Google or DeepL.
Speaches FAQ
How much RAM does Speaches need?
Speaches does not publish an official RAM figure, so we do not state one.
Does Speaches need a GPU?
Optional (CUDA image). A CPU image is available.
How much does it cost to self-host Speaches?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is Speaches free for commercial use?
Speaches is licensed under MIT (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed. Speech models keep their own licenses. This is a summary, not legal advice.
What are common problems when self-hosting Speaches?
Separate images and Compose files exist for CPU, CUDA and CUDA with CDI. Pick the one matching your host, or GPU acceleration will not be used.
Is Speaches still maintained?
Activity is low (no commit in 180+ days). Last commit: Apr 18, 2026. Latest release: v0.9.0-rc.3 (Dec 27, 2025). Checked Oct 22, 2026.
How do I install Speaches?
The official method is Docker. The exact commands are in the "How to deploy" section above and in the official instructions: https://speaches.ai/installation/
What are self-hosted alternatives to Speaches?
Other apps in Speech & translation: LibreTranslate.
Sources
- GitHub repository: github.com/speaches-ai/speaches
- Official documentation, Hardware requirements, Deploy instructions, Gotcha 1: speaches.ai/installation/
- License text: github.com/speaches-ai/speaches/blob/master/LICENSE
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-22. Spotted something out of date? Tell us.