Results for "text-to-speech"

100 matches found.

hexgrad

hexgrad/Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to large...

🗣️ text-to-speech 9,828,072
coqui

coqui/XTTS-v2

No description available.

🗣️ text-to-speech 8,081,180
ResembleAI

ResembleAI/chatterbox

No description available.

🗣️ text-to-speech 2,008,426
Qwen

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

No description available.

🗣️ text-to-speech 1,080,797
SWivid

SWivid/F5-TTS

No description available.

🗣️ text-to-speech 800,530
microsoft

microsoft/VibeVoice-Realtime-0.5B

No description available.

🗣️ text-to-speech 490,522
Qwen

Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

No description available.

🗣️ text-to-speech 384,485
parler-tts

parler-tts/parler-tts-mini-multilingual-v1.1

No description available.

🗣️ text-to-speech 278,126
ai4bharat

ai4bharat/indic-parler-tts

No description available.

🗣️ text-to-speech 273,637
bosonai

bosonai/higgs-audio-v2-generation-3B-base

No description available.

🗣️ text-to-speech 271,142
Qwen

Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice

No description available.

🗣️ text-to-speech 268,849
Qwen

Qwen/Qwen3-TTS-12Hz-0.6B-Base

No description available.

🗣️ text-to-speech 256,696
kenpath

kenpath/svara-tts-v1

No description available.

🗣️ text-to-speech 252,133
myshell-ai

myshell-ai/MeloTTS-English

No description available.

🗣️ text-to-speech 222,878
microsoft

microsoft/VibeVoice-1.5B

No description available.

🗣️ text-to-speech 221,155
myshell-ai

myshell-ai/MeloTTS-Japanese

No description available.

🗣️ text-to-speech 207,399
hypaai

hypaai/Hypa_Orpheus-3b-0.1-ft-unsloth-merged_16bit

No description available.

🗣️ text-to-speech 189,356
facebook

facebook/mms-tts-hat

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 173,105
facebook

facebook/mms-tts-kor

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 170,695
sesame

sesame/csm-1b

No description available.

🗣️ text-to-speech 139,570
kyutai

kyutai/tts-0.75b-en-public

The model architecture is a hierarchical Transformer that consumes tokenized text and generateds audio tokenized by Mimi, see the Moshi pape...

🗣️ text-to-speech 138,089
facebook

facebook/mms-tts-eng

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 133,043
myshell-ai

myshell-ai/MeloTTS-Chinese

No description available.

🗣️ text-to-speech 126,555
canopylabs

canopylabs/3b-de-ft-research_release

No description available.

🗣️ text-to-speech 114,598
SWivid

SWivid/E2-TTS

No description available.

🗣️ text-to-speech 112,403
microsoft

microsoft/speecht5_tts

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-m...

🗣️ text-to-speech 110,885
maya-research

maya-research/maya1

No description available.

🗣️ text-to-speech 96,793
Aratako

Aratako/MioTTS-2.6B

No description available.

🗣️ text-to-speech 94,112
kugelaudio

kugelaudio/kugelaudio-0-open

No description available.

🗣️ text-to-speech 92,279
OpenMOSS-Team

OpenMOSS-Team/MOSS-TTS

No description available.

🗣️ text-to-speech 91,854
facebook

facebook/hf-seamless-m4t-medium

No description available.

🗣️ text-to-speech 88,986
nari-labs

nari-labs/Dia-1.6B

No description available.

🗣️ text-to-speech 83,077
onnx-community

onnx-community/Kokoro-82M-v1.0-ONNX

No description available.

🗣️ text-to-speech 75,247
mahwizzzz

mahwizzzz/orpheus-urdu-tts

The Orpheus Urdu TTS model is a fine-tuned version of the Orpheus 3B text-to-speech model specifically adapted for Urdu language. This exper...

🗣️ text-to-speech 75,146
neuphonic

neuphonic/neutts-air-q4-gguf

NeuTTS Air is built off Qwen 0.5B - a lightweight yet capable language model optimised for text understanding and generation - as well as a ...

🗣️ text-to-speech 69,708
myshell-ai

myshell-ai/MeloTTS-Spanish

No description available.

🗣️ text-to-speech 63,622
suno

suno/bark

The following is additional information about the models released here. Bark is a series of three transformer models that turn text into aud...

🗣️ text-to-speech 60,704
kyutai

kyutai/tts-1.6b-en_fr

The model architecture is a hierarchical Transformer that consumes tokenized text and generateds audio tokenized by Mimi, see the Moshi pape...

🗣️ text-to-speech 58,702
Nextcloud-AI

Nextcloud-AI/Kokoro-82M

Kokoro models duplicated as-is from https://huggingface.co/hexgrad/Kokoro-82M for usage in local text to speech app....

🗣️ text-to-speech 49,732
OpenMOSS-Team

OpenMOSS-Team/MOSS-TTS-Local-Transformer

No description available.

🗣️ text-to-speech 49,697
OpenMOSS-Team

OpenMOSS-Team/MOSS-TTS-Realtime

No description available.

🗣️ text-to-speech 46,417
canopylabs

canopylabs/orpheus-3b-0.1-pretrained

No description available.

🗣️ text-to-speech 40,940
onnx-community

onnx-community/Kokoro-82M-ONNX

No description available.

🗣️ text-to-speech 38,323
myshell-ai

myshell-ai/MeloTTS-Korean

No description available.

🗣️ text-to-speech 33,520
speechbrain

speechbrain/tts-hifigan-libritts-22050Hz

No description available.

🗣️ text-to-speech 31,521
suno

suno/bark-small

The following is additional information about the models released here. Bark is a series of three transformer models that turn text into aud...

🗣️ text-to-speech 29,537
facebook

facebook/mms-tts-por

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 29,145
unsloth

unsloth/orpheus-3b-0.1-ft

No description available.

🗣️ text-to-speech 29,003
myshell-ai

myshell-ai/MeloTTS-French

No description available.

🗣️ text-to-speech 26,695
canopylabs

canopylabs/orpheus-3b-0.1-ft

No description available.

🗣️ text-to-speech 22,564
nari-labs

nari-labs/Dia-1.6B-0626

No description available.

🗣️ text-to-speech 21,227
OpenMOSS-Team

OpenMOSS-Team/MOSS-TTSD-v1.0

No description available.

🗣️ text-to-speech 20,519
OuteAI

OuteAI/Llama-OuteTTS-1.0-1B

Oute A I outeai.com ......

🗣️ text-to-speech 19,759
pnnbao-ump

pnnbao-ump/VieNeu-TTS-0.3B-q4-gguf

No description available.

🗣️ text-to-speech 19,435
Misha24-10

Misha24-10/F5-TTS_RUSSIAN

No description available.

🗣️ text-to-speech 19,308
mlx-community

mlx-community/Qwen3-TTS-12Hz-0.6B-Base-8bit

No description available.

🗣️ text-to-speech 18,525
mlx-community

mlx-community/Kokoro-82M-bf16

No description available.

🗣️ text-to-speech 17,581
IndexTeam

IndexTeam/IndexTTS-2

No description available.

🗣️ text-to-speech 15,717
hexgrad

hexgrad/Kokoro-82M-v1.1-zh

🐈 GitHub: https://github.com/hexgrad/kokoro...

🗣️ text-to-speech 15,472
inclusionAI

inclusionAI/Ming-omni-tts-0.5B

No description available.

🗣️ text-to-speech 14,406
mlx-community

mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit

No description available.

🗣️ text-to-speech 14,373
ekwek

ekwek/Soprano-1.1-80M

No description available.

🗣️ text-to-speech 13,880
pnnbao-ump

pnnbao-ump/VieNeu-TTS-q4-gguf

No description available.

🗣️ text-to-speech 13,758
maya-research

maya-research/Veena

Veena is a 3B parameter autoregressive transformer model based on the Llama architecture. It is designed to synthesize high-quality speech f...

🗣️ text-to-speech 12,185
pnnbao-ump

pnnbao-ump/VieNeu-TTS-0.3B

No description available.

🗣️ text-to-speech 12,005
marksverdhai

marksverdhai/vibevoice-7b-bnb-4bit

| Property | Value | |----| | Base Model | vibevoice/VibeVoice-7B | | Quantization | bitsandbytes NF4 (4-bit) | | VRAM Usage | ~6.2 GB | | M...

🗣️ text-to-speech 12,003
Zyphra

Zyphra/Zonos-v0.1-transformer

No description available.

🗣️ text-to-speech 11,994
HKUSTAudio

HKUSTAudio/Llasa-1B

No description available.

🗣️ text-to-speech 11,906
nari-labs

nari-labs/Dia2-2B

No description available.

🗣️ text-to-speech 11,492
Xenova

Xenova/speecht5_tts

No description available.

🗣️ text-to-speech 11,213
parler-tts

parler-tts/parler-tts-large-v1

No description available.

🗣️ text-to-speech 10,844
neuphonic

neuphonic/neutts-air

NeuTTS Air is built off Qwen 0.5B - a lightweight yet capable language model optimised for text understanding and generation - as well as a ...

🗣️ text-to-speech 10,640
mlx-community

mlx-community/Qwen3-TTS-12Hz-1.7B-Base-bf16

No description available.

🗣️ text-to-speech 9,823
OpenMOSS-Team

OpenMOSS-Team/MOSS-VoiceGenerator

No description available.

🗣️ text-to-speech 9,607
parler-tts

parler-tts/parler-tts-mini-v1

No description available.

🗣️ text-to-speech 9,484
pnnbao-ump

pnnbao-ump/VieNeu-TTS

No description available.

🗣️ text-to-speech 9,062
vibevoice

vibevoice/VibeVoice-1.5B

No description available.

🗣️ text-to-speech 8,858
akh99

akh99/veena-hinglish

Veena Hinglish is a LoRA fine-tuned text-to-speech model optimized for generating natural-sounding speech in Hinglish. The model uses SNAC (...

🗣️ text-to-speech 8,320
unsloth

unsloth/csm-1b

See our collection for all our TTS model uploads. Learn to fine-tune TTS models - Read our Guide. Unsloth Dynamic 2.0 achieves superior accu...

🗣️ text-to-speech 8,197
vibevoice

vibevoice/VibeVoice-7B

No description available.

🗣️ text-to-speech 8,185
canopylabs

canopylabs/3b-ko-ft-research_release

No description available.

🗣️ text-to-speech 7,724
unsloth

unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit

No description available.

🗣️ text-to-speech 7,563
facebook

facebook/mms-tts-tgl

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 7,441
ai4bharat

ai4bharat/IndicF5

No description available.

🗣️ text-to-speech 7,380
Supertone

Supertone/supertonic

No description available.

🗣️ text-to-speech 7,116
aoi-ot

aoi-ot/VibeVoice-Large

No description available.

🗣️ text-to-speech 6,917
neuphonic

neuphonic/neutts-nano-q4-gguf

NeuTTS Nano models are designed for maximum speed per parameter while retaining strong speaker similarity and naturalness: - Backbone: compa...

🗣️ text-to-speech 6,745
facebook

facebook/mms-tts-hin

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 6,723
saheedniyi

saheedniyi/YarnGPT2

Developed by: Saheedniyi - Model type: Text-to-Speech - Language(s) (NLP): English--> Nigerian Accented English - Finetuned from: HuggingFac...

🗣️ text-to-speech 6,637
Supertone

Supertone/supertonic-2

No description available.

🗣️ text-to-speech 6,529
openbmb

openbmb/VoxCPM1.5

No description available.

🗣️ text-to-speech 6,526
neuphonic

neuphonic/neutts-nano

NeuTTS Nano models are designed for maximum speed per parameter while retaining strong speaker similarity and naturalness: - Backbone: compa...

🗣️ text-to-speech 6,365
OuteAI

OuteAI/Llama-OuteTTS-1.0-1B-GGUF

Oute A I outeai.com ......

🗣️ text-to-speech 6,326
FunAudioLLM

FunAudioLLM/Fun-CosyVoice3-0.5B-2512

No description available.

🗣️ text-to-speech 6,308
fishaudio

fishaudio/s1-mini

No description available.

🗣️ text-to-speech 6,098
cocktailpeanut

cocktailpeanut/oa

No description available.

🗣️ text-to-speech 5,555
cartesia

cartesia/sesame-csm-1b-gguf

No description available.

🗣️ text-to-speech 5,366
facebook

facebook/mms-tts-orm

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 5,365
facebook

facebook/mms-tts-kir

VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a...

🗣️ text-to-speech 5,292
fishaudio

fishaudio/fish-speech-1.5

No description available.

🗣️ text-to-speech 5,117