LJ Speech samples (public domain) for voice cloning:
- Standard: alloy, echo, fable, onyx, nova, shimmer
- Extended: amber, breeze, coral, dawn, ember, frost,
glow, haze, ivy, jade, kite, lark, mist, nectar
146 lines
4.8 KiB
YAML
146 lines
4.8 KiB
YAML
# uncloseai-speech Voice Configuration
|
|
# Diverse voice samples for Qwen3-TTS voice cloning
|
|
#
|
|
# Standard voices: alloy, echo, fable, onyx, nova, shimmer
|
|
# Extended voices: amber, breeze, coral, dawn, ember, frost,
|
|
# glow, haze, ivy, jade, kite, lark, mist, nectar
|
|
#
|
|
# Source: LJ Speech Dataset (public domain)
|
|
# https://keithito.com/LJ-Speech-Dataset/
|
|
|
|
tts-1-qwen:
|
|
|
|
# neutral, balanced - clear professional delivery
|
|
alloy:
|
|
ref_audio: cloned-voices/alloy.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
|
|
|
|
# clear, measured - precise enunciation
|
|
echo:
|
|
ref_audio: cloned-voices/echo.wav
|
|
ref_text: "yet the art did not begin to flourish in Europe until the middle of the fifteenth century."
|
|
language: English
|
|
|
|
# expressive, storyteller - engaging narration
|
|
fable:
|
|
ref_audio: cloned-voices/fable.wav
|
|
ref_text: "The type of this time in spite of the many failures is in the main admirable"
|
|
language: English
|
|
|
|
# deep, dramatic - authoritative tone
|
|
onyx:
|
|
ref_audio: cloned-voices/onyx.wav
|
|
ref_text: "For although the Chinese seem to have known its art of printing with engraved wooden blocks"
|
|
language: English
|
|
|
|
# warm, friendly - approachable delivery
|
|
nova:
|
|
ref_audio: cloned-voices/nova.wav
|
|
ref_text: "the art of block printing was known in Europe during the first half of the fifteenth century"
|
|
language: English
|
|
|
|
# soft, gentle - calm and soothing
|
|
shimmer:
|
|
ref_audio: cloned-voices/shimmer.wav
|
|
ref_text: "in being comparatively modern."
|
|
language: English
|
|
|
|
# warm amber glow - inviting and comfortable
|
|
amber:
|
|
ref_audio: cloned-voices/amber.wav
|
|
ref_text: "it may be necessary to turn over many examples before finding one that is even passable"
|
|
language: English
|
|
|
|
# light breeze - airy and refreshing
|
|
breeze:
|
|
ref_audio: cloned-voices/breeze.wav
|
|
ref_text: "the commonest, that is to say, the most familiar faces, depart a good deal from those of the least common types"
|
|
language: English
|
|
|
|
# coral reef - vibrant and lively
|
|
coral:
|
|
ref_audio: cloned-voices/coral.wav
|
|
ref_text: "The practice of the earlier printers led them to attach the pieces of the text carefully together"
|
|
language: English
|
|
|
|
# early dawn - fresh and hopeful
|
|
dawn:
|
|
ref_audio: cloned-voices/dawn.wav
|
|
ref_text: "This practice has spoiled many books from many different points of view"
|
|
language: English
|
|
|
|
# glowing ember - warm with depth
|
|
ember:
|
|
ref_audio: cloned-voices/ember.wav
|
|
ref_text: "Indeed, it is still the case that a good many examples of mediaeval printing"
|
|
language: English
|
|
|
|
# winter frost - crisp and clear
|
|
frost:
|
|
ref_audio: cloned-voices/frost.wav
|
|
ref_text: "In spite of the many errors both of commission and omission in which the early printers"
|
|
language: English
|
|
|
|
# soft glow - gentle radiance
|
|
glow:
|
|
ref_audio: cloned-voices/glow.wav
|
|
ref_text: "as the types used are of necessity identical, it is obvious that for the sake of appearance"
|
|
language: English
|
|
|
|
# morning haze - dreamy and ethereal
|
|
haze:
|
|
ref_audio: cloned-voices/haze.wav
|
|
ref_text: "the character of the letters forming a font"
|
|
language: English
|
|
|
|
# climbing ivy - natural and organic
|
|
ivy:
|
|
ref_audio: cloned-voices/ivy.wav
|
|
ref_text: "which allows for the production of books of all degrees of excellence"
|
|
language: English
|
|
|
|
# jade stone - smooth and precious
|
|
jade:
|
|
ref_audio: cloned-voices/jade.wav
|
|
ref_text: "he must be able to draw his letter well and make his curves in geometry"
|
|
language: English
|
|
|
|
# flying kite - free and playful
|
|
kite:
|
|
ref_audio: cloned-voices/kite.wav
|
|
ref_text: "From time to time this subject has been much debated"
|
|
language: English
|
|
|
|
# morning lark - cheerful and bright
|
|
lark:
|
|
ref_audio: cloned-voices/lark.wav
|
|
ref_text: "Again, it is of the utmost importance that the types which we call the roman"
|
|
language: English
|
|
|
|
# soft mist - mysterious and intriguing
|
|
mist:
|
|
ref_audio: cloned-voices/mist.wav
|
|
ref_text: "Now, as all books not primarily intended as picture-books consist principally of types composed"
|
|
language: English
|
|
|
|
# sweet nectar - rich and delightful
|
|
nectar:
|
|
ref_audio: cloned-voices/nectar.wav
|
|
ref_text: "The other matter to be considered is the arrangement of the printed matter"
|
|
language: English
|
|
|
|
# Other TTS engines (disabled by default)
|
|
# Uncomment and configure to enable
|
|
|
|
# tts-1:
|
|
# # Piper TTS (fast CPU inference)
|
|
# alloy:
|
|
# model: /app/voices/en/en_US/libritts_r/medium/en_US-libritts_r-medium.onnx
|
|
# speaker: 79
|
|
|
|
# tts-1-hd:
|
|
# # XTTS v2 (voice cloning)
|
|
# alloy:
|
|
# model: xtts
|
|
# speaker: voices/alloy.wav
|