Transcribes audio messages using OpenAIs Whisper
2.7K
The Matrix Speech‑To‑Text Bot is a powerful tool that transcribes audio messages using OpenAI Whisper. It is built on top of Simple‑Matrix‑Bot‑Lib and leverages the fast inference engine provided by whisper.cpp.
Source: GitHub
tiny, tiny.en, base, small, medium, large‑v3, …) and languages.You can deploy it using docker-compose:
services:
matrix-stt-bot:
image: ftcaplan/matrix-stt-bot
restart: on-failure
volumes:
- ./data/:/data/
environment:
- "HOMESERVER=https://matrix.example.com"
- "USERNAME=@stt-bot:example.com"
- "PASSWORD=<password>"
- "ASR_MODEL=tiny"
- "ASR_LANGUAGE=en"
# optional: pass rendering device to container to enable Vulkan support
devices:
- /dev/dri
You can choose a model by setting it with ASR_MODEL. Available models include tiny.en, tiny, base, small, medium, and large-v3. The default is ASR_MODEL=tiny.
You can authenticate using tokens instead of a password: Set LOGIN_TOKEN=<login-token> or ACCESS_TOKEN=<access-token> instead of PASSWORD=<password>.
To restrict commands to specific users, you can set up an allowlist using regular expressions of Matrix user IDs. This feature allows you to specify which users are allowed to send commands to the bot.
ALLOWLIST environment variable is defined, the bot will parse it and use it as the allowlist.ALLOWLIST=^@user1:example.com$,^@user2:example.com$ALLOWLIST is not defined, the bot will only allow commands from users of the bot's homeserver.Content type
Image
Digest
sha256:ee6bd8764…
Size
186.6 MB
Last updated
about 2 months ago
docker pull ftcaplan/matrix-stt-bot