Speaches
Self-hosted OpenAI-compatible server for speech-to-text and text-to-speech.
Overview
Speaches serves faster-whisper transcription and Kokoro or Piper TTS behind the OpenAI audio API, so apps built for OpenAI can use local voice models. It runs in Docker with GPU or CPU.
- OpenAI-compatible endpoints
- Streaming transcription
- Dynamic model loading
- Realtime API support
Our verdict
What we like
- Drop-in local replacement
- Docker ready
Watch out for
- No GUI
Works with these providers
Keys from these providers work in this app. Usage is billed by the provider at its list price.
BYOK Key Safety Score
Key handling in Speaches
Grade A
Your key is stored on your device and requests go directly to the provider.
- Key storage40/40
Key stays on your device; requests go direct to the provider.
- Auditable code25/25
Open source: anyone can verify how keys are handled.
- Self-hosting15/15
Can run entirely on your own infrastructure.
- Offline option10/10
Supports local models, so no key is needed at all for private work.
- Provider choice2/10
1 provider option, which lets you pick the provider whose data terms you trust.
Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.
Speaches FAQ
- Does Speaches support bring your own key?
- Yes. Speaches accepts your own API key from OpenAI-compatible. Usage is billed by the provider at its API rates.
- Where does Speaches store my API key?
- On your device. Requests go directly from Speaches to the provider. Its BYOK Tools Key Safety Score is 92/100.
- Is Speaches free?
- Open source: Free & open source. API usage is billed separately by your model provider.
- Is Speaches open source?
- Yes. The source code is at https://github.com/speaches-ai/speaches. It can also be self-hosted.
- Can Speaches run local models?
- Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
- Which platforms does Speaches support?
- Self-hosted.
Community reviews
No reviews yet.
Alternatives to Speaches
All voice & dictation →AllTalk TTS
Voice & Dictation
Local text-to-speech server with voice cloning and many engines.
ebook2audiobook
Voice & Dictation
Convert ebooks to audiobooks with chapters using local TTS models.
Podcastfy
Voice & Dictation
Turn documents, URLs and videos into AI-generated podcast conversations.
MacWhisper
Voice & Dictation
Transcribe audio and video files on your Mac with Whisper.
Superwhisper
Voice & Dictation
AI voice dictation for Mac and iOS with local and cloud models.
VoiceInk
Voice & Dictation
Open-source Mac dictation app with local Whisper and AI enhancement.