piper is a fast, local neural text to speech system that sounds great and is optimized for the Raspberry Pi 4. This container provides a Wyoming protocol server for Piper.
Generated from the image's own configuration. Replace the /path/to folders with real paths on your host.
---
services:
piper:
image: lscr.io/linuxserver/piper:latest
container_name: piper
environment:
- PUID=1000
- PGID=1000
- TZ=Etc/UTC
- PIPER_VOICE=en_US-lessac-medium
- LOCAL_ONLY= # optional
- PIPER_LENGTH=1.0 # optional
- PIPER_NOISE=0.667 # optional
- PIPER_NOISEW=0.333 # optional
- PIPER_SPEAKER=0 # optional
- NO_STREAMING= # optional
volumes:
- /path/to/piper/data:/config
ports:
- 10200:10200
restart: unless-stopped| Port | Function | Required |
|---|---|---|
| 10200:10200 | Wyoming connection port. | required |
| Variable | Function | Required |
|---|---|---|
| PUID=1000 | User ID | required |
| PGID=1000 | Group ID | required |
| TZ=Etc/UTC | Timezone | required |
| PIPER_VOICE=en_US-lessac-medium | The [Piper voice](https://huggingface.co/rhasspy/piper-voices/tree/main) to use, in the format `<language>-<name>-<quality>` | required |
| LOCAL_ONLY= | If set to `true`, or any other value, the container will not attempt to download models from HuggingFace and will only use locally-provided models. | optional |
| PIPER_LENGTH=1.0 | Voice speaking rate, 1.0 is default with < 1.0 being faster and > 1.0 being slower. | optional |
| PIPER_NOISE=0.667 | Controls the variability of the voice by adding noise. Values above 1 will start to degrade audio. | optional |
| PIPER_NOISEW=0.333 | Controls the variability of speaking cadence. Values above 1 produce extreme stutters and pauses. | optional |
| PIPER_SPEAKER=0 | Speaker number to use if the voice supports multiple speakers. | optional |
| NO_STREAMING= | Setting to `true`, or any other value, will disable support for streaming audio on sentence boundaries. | optional |
| Path | Function | Required |
|---|---|---|
| /config | Local path for piper config files. | required |
Pulling :latest picks the right one for your host automatically.
amd64-latestarm64v8-latest:latestStable releases:gpuReleases with Nvidia GPU support (amd64 only)Rebase to Ubuntu Resolute.
Add support for local only mode.
Add streaming support.
Related
v3.8.1-ls10
faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This container provides a Wyoming protocol server for faster-whisper.