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

Use LJ Speech sample for voice cloning (Alibaba Cloud URL blocked)

Browse source
This commit is contained in:
russell@unturf.com 2026-01-26 16:28:39 -05:00
parent ad6a4d4990
commit 6b4f66dcf5
2 changed files with 84 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

27
voice_to_speaker.default.yaml
View file

@ -6,40 +6,41 @@ tts-1-qwen:
# Each voice requires ref_audio (reference audio) and ref_text (transcript of the audio)
# Language: Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
# Default voice - using Qwen's example clone audio
# Default voice - using LJ Speech sample (public domain)
# Original Qwen demo URL (https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav) is blocked
alloy:
ref_audio: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav
ref_text: "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it!"
ref_audio: voices/samples/lj_speech.wav
ref_text: "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
language: English
# Echo - same sample, different name for compatibility
echo:
ref_audio: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav
ref_text: "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it!"
ref_audio: voices/samples/lj_speech.wav
ref_text: "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
language: English
# Fable - same sample
fable:
ref_audio: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav
ref_text: "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it!"
ref_audio: voices/samples/lj_speech.wav
ref_text: "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
language: English
# Onyx - same sample
onyx:
ref_audio: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav
ref_text: "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it!"
ref_audio: voices/samples/lj_speech.wav
ref_text: "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
language: English
# Nova - same sample
nova:
ref_audio: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav
ref_text: "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it!"
ref_audio: voices/samples/lj_speech.wav
ref_text: "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
language: English
# Shimmer - same sample
shimmer:
ref_audio: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav
ref_text: "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it!"
ref_audio: voices/samples/lj_speech.wav
ref_text: "Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition"
language: English
# Custom voice example - add your own reference audio