Skip to content
BYOK Tools

Speaches

Self-hosted OpenAI-compatible server for speech-to-text and text-to-speech.

4.0 editor score•Voice & Dictation•Free & open source

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

How we score
92/ 100

Grade A

Your key is stored on your device and requests go directly to the provider.

  • Key storage

    Key stays on your device; requests go direct to the provider.

    40/40
  • Auditable code

    Open source: anyone can verify how keys are handled.

    25/25
  • Self-hosting

    Can run entirely on your own infrastructure.

    15/15
  • Offline option

    Supports local models, so no key is needed at all for private work.

    10/10
  • Provider choice

    1 provider option, which lets you pick the provider whose data terms you trust.

    2/10

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.