Post-Training Thoughts
pinned
4
#92 opened 15 days ago
by
hexgrad
[Rule] Try on Colab before posting a technical issue
pinned
4
#45 opened 30 days ago
by
hexgrad
Intonation howto
#125 opened about 14 hours ago
by
Dunc4n1dah0
Is there an empiric explanation to the speed parameter of the generation function?
#124 opened 1 day ago
by
cgarijo-Ci21
Controlling Pauses?
#123 opened 2 days ago
by
banank1989
v0.19 and v1.0 versions Comparison: Advancements and Limitations
3
#121 opened 2 days ago
by
MaverickBuffoon
How can use this model with clone voice?
3
#118 opened 4 days ago
by
bctan
Training other language
1
#116 opened 5 days ago
by
Tobe2d
使用离线本地模型
2
#114 opened 5 days ago
by
whereAlone
How does speed up work?
#110 opened 7 days ago
by
yukiarimo
Is there a way to add new voices or pronunciations to Kokoro
3
#108 opened 8 days ago
by
GinoskoAI
How does one add emotion to the voice?
3
#107 opened 8 days ago
by
vijay120
Kokoro can also speak untrained languages ?! (examples: Greek and Armenian).
2
#105 opened 9 days ago
by
vahanAI
Question about accessing private Space via API
4
#103 opened 11 days ago
by
bezprzesadyco
Inconsistency in speed, some sentences are being spoken fast
#101 opened 12 days ago
by
aagawade1999
Made a Webapp for Kokoro (fixed missing first chunk when downloading)
9
#100 opened 12 days ago
by
alexkyk
Issues with "espeak not installed in your system" - Mac M1 - Solved
#98 opened 13 days ago
by
AndrewCoote
Segmenting Text for Token Limitations - Code Provided for v0.19
1
#97 opened 14 days ago
by
gmacgmac
Is v1.0 going to get onnx formatted models?
6
#96 opened 14 days ago
by
belisarius
Kokoro is skipping names
1
#91 opened 15 days ago
by
CoolIce537
Chinese problem with zf_xiaobei
5
#89 opened 15 days ago
by
hanswang1973
How to generate single audio file for longer texts.
1
#87 opened 16 days ago
by
AgarVaibhav
Dataset for german language
10
#86 opened 16 days ago
by
junkstage
Android TTS app
7
#80 opened 18 days ago
by
ct-2
Will Indonesian language available?
#79 opened 19 days ago
by
Syams
WARNING:phonemizer:words count mismatch on 100.0% of the lines (1/1) Truncated to 510 tokens
1
#76 opened 21 days ago
by
Mentrasss
The generated audio is a bit small. How can I increase the volume in the code?
1
#74 opened 21 days ago
by
mayixb
Unofficial Endpoints: Use at your own risk, no support offered
1
#73 opened 23 days ago
by
hexgrad
generate_full is cut unexpectedly.
4
#70 opened 23 days ago
by
konecth
Curb Your Expectations: Data & Architecture Limitations
13
#69 opened 23 days ago
by
hexgrad
Where is the close-sourced encoder of this repo?
#66 opened 25 days ago
by
cgarijo-Ci21
bm_george = Discover Daily by Perplexity podcast voice
#65 opened 25 days ago
by
anrichvdwalt
Windows ready script, including chunking too long input by sentences and then token count (modest count). Use input.txt file as your text input for the model. Tested on Windows 11
4
#64 opened 25 days ago
by
ADHDev
How do novices deploy Kokoro-82M locally?
3
#63 opened 26 days ago
by
mayixb
Adding defined period pauses to the input text file
5
#61 opened 26 days ago
by
vijay120
How to access other languages besides British and American English?
#59 opened 27 days ago
by
Mr-Andrew
CoreML support
1
#56 opened 28 days ago
by
szykadam
Kokoro-82m ONNX Runtime Deployment on HuggingFace Space
#55 opened 28 days ago
by
yakhyo
How to create custom voice pack?
5
#53 opened 29 days ago
by
Meshwa
Voice Embedding JSON Files
2
#52 opened 29 days ago
by
ecyht2
Safetensors version of Kokoro?
2
#51 opened 29 days ago
by
jattoedaltni
Permissively licensed transcription to International Phonetic Alphabet (IPA) in Python
6
#50 opened 29 days ago
by
davidmezzetti
How to train this model if wan to use self voice data
2
#47 opened 29 days ago
by
jall
Using kokoro-82M to animate face, super fast!
3
#40 opened about 1 month ago
by
warmshao
Is it possible to change seed or temperature?
#38 opened about 1 month ago
by
SporkySporkness
Free kokoro TTS endpoint - no strings attached.
2
#37 opened about 1 month ago
by
mhenrichsen
Guys, Rust inference of Kokoro!
2
#35 opened about 1 month ago
by
lucasjin
Is it possible to use the model directly?
1
#34 opened about 1 month ago
by
asif00
Complete newbie with questions about use for Android
2
#33 opened about 1 month ago
by
therewasoncethisguy
can we upload custom voices and generate tts using it using api inference?
1
#31 opened about 1 month ago
by
manancode