Faster-Qwen3-TTS-Wyoming

Local Faster Qwen3-TTS with a WebUI, an OpenAI-compatible streaming API, and an integrated Wyoming TTS adapter for Home Assistant.

  • AI
  • Home Automation
  • Tools & Utilities
Local Faster Qwen3-TTS with a WebUI, an OpenAI-compatible streaming API, and an integrated Wyoming TTS adapter for Home Assistant. Both interfaces share one NVIDIA GPU model instance.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

54/100 Fair

Maintained
69last commit 82 days ago
Popular
209 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data
Security check
85no serious findings, CI, tests, new single-developer project

Based on 4 of 5 factors.

Availability: platform listings confirmed today, links checked 22 days ago

GitHub stars
9
Open issues
0
Last commit
2026-08-31
Latest release
v1.0.3
License
MIT
Activity
stale

Checked 7 days ago - source: GitHub (agrestisdavid/faster-qwen3-tts-wyoming)

Resources & Compatibility

Requirements not published yet.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Install the stable speech library first Run `pip install faster-whisper` (pip is Python's package installer) so the app has the speech-to-text package it needs. Without it, the app can't turn audio into text and will usually fail when it starts. source
  • Pick and save a speech model locally Choose a speech model (the pre-trained part that listens to audio and predicts words) from the available list and save it in a stable folder using `download_model()`. If you skip this, the app may not find a valid model or may repeatedly download a large file. source
  • Optionally skip silence with a VAD If your recordings have long pauses, use a VAD (a filter that looks for actual speech and ignores silence). Without it, the app can waste time processing silence or create less useful segments. source

Fetched 53 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Does the Docker container run the local TTS worker and the Home Assistant Wyoming adapter together?

Yes. The project bundles a local Faster Qwen3-TTS worker and a Wyoming TTS adapter in one NVIDIA-capable Docker container.

What settings can make the Wyoming TTS start speaking faster?

For a faster start, keep non_streaming_mode=false and appropriately reduce chunk_size.

How can I get timestamp data for text highlighting?

A forum discussion describes creating timestamp data with a Qwen3-ForcedAligner workflow for Faster Qwen3-TTS audio, and mentions an OpenAI-compatible endpoint.

Are there tutorials for voice cloning, voice design, and custom voices?

An NVIDIA forum playbook covers running faster Qwen3-TTS for voice cloning, voice design, and custom voices on DGX Spark.

Answers sourced from forums.developer.nvidia.com, forums.developer.nvidia.com, github.com, github.com

Community

Collected 49 days ago - public community threads