engineering/uncloseai.com
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add make voices-qwen to self-hosting instructions

Browse source 
Explain how to download the 42+ cloned voice samples from LibriSpeech
using the new Makefile target. Updated on both the main TTS page and
the Qwen3-TTS subpage.
This commit is contained in:
russell@unturf.com 2026-01-27 17:31:17 -05:00
parent 363dde30f0
commit df040d4f70
2 changed files with 11 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

15
public/text-to-speech.html
View file

@ -175,20 +175,23 @@ client.audio.speech.create(
<pre><code class="bash">git clone https://git.unturf.com/engineering/unturf/uncloseai-speech.git
cd uncloseai-speech
# Deploy with GPU (voice cloning engine, default)
# Deploy with GPU (Qwen3-TTS, default)
make deploy
# Or CPU-only (works anywhere, slower)
make deploy-cpu
# Test it (model downloads automatically on first use)
# Download 42+ cloned voice samples from LibriSpeech
make voices-qwen
# Test it (Qwen3-TTS model ~3.4GB downloads automatically on first use)
make test
# Enable additional engines
make voices-piper # Fast Synthesis
make voices-xtts # HD Voice Cloning
make voices-silero # Multilingual CPU
make voices-kokoro # Lightweight</code></pre>
make voices-piper # Piper TTS
make voices-xtts # XTTS v2
make voices-silero # Silero TTS
make voices-kokoro # Kokoro TTS</code></pre>
<p>For full documentation, see the <a href="https://git.unturf.com/engineering/unturf/uncloseai-speech" target="_blank">uncloseai-speech repository</a>.</p>

3
public/tts/voice-cloning.html
View file

@ -154,9 +154,10 @@ client.audio.speech.create(
<pre><code class="bash">git clone https://git.unturf.com/engineering/unturf/uncloseai-speech.git
cd uncloseai-speech
make deploy
make voices-qwen # Download 42+ cloned voice samples from LibriSpeech
make test</code></pre>
<p>The model downloads automatically on first use (~3.4 GB). Voice samples are included in the repo.</p>
<p>The Qwen3-TTS model (~3.4 GB) downloads automatically on first use. The <code>make voices-qwen</code> target runs <code>scripts/download_diverse_voices.py</code>, which pulls speaker samples from the LibriSpeech corpus and assigns them permanent human names via the voice registry.</p>
<p><a href="/text-to-speech.html"><strong>&larr; Back to Text-to-Speech overview</strong></a></p>