Running
on
Zero
9
Step Audio 2 Mini
π₯
Generate audio responses from text or voice input
Running
on
Zero
3
EchoX
π₯
An end-to-end speech large language model.
Runtime error
32
VibeVoice Demo
π
Launch VibeVoice demo for text-to-speech conversion
Running
on
T4
128
Pretrained pipelines
πΉ
Identify speakers in an audio file
Running
on
T4
204
ProsekaTTS
π’
Generate speech from text in Japanese
Running
5
Multilingual Anime TTS
π
Generate anime character voice
Running
411
tts Text To Speech
π
Text-to-speech (TTS) with Next-gen Kaldi
Running
on
L4
691
StyleTTS 2
π£
Efficient, fast, and natural text to speech with StyleTTS 2!
Running
111
Podcastify
π£
Turn Any Article to Podcast
Running
303
Whisper Speaker Diarization
π£
Separate speakers in audio recordings
Running
on
Zero
335
Realtime Whisper Turbo
π€―
Realtime implementation of Whisper large turbo
Running
on
Zero
606
Spanish F5
π£
Spanish finetune for the original F5 model.
Running
3
Whisper Web
π€
Transcribe audio to text
Running
on
Zero
830
Sesame CSM
π±
Conversational speech generation
Running
345
Qwen2.5 Omni 7B Demo
π
Generate text and speech from audio, video, and text inputs
Running
13
ONNX ASR
π’
ASR demo using onnx-asr
Running
on
Zero
MCP
368
Higgs Audio Demo
π€
Higgs Audio Demo
Running
73
KittenTTS Web
π±
State-of-the-art TTS model under 25MB
Running
on
Zero
22
MGM Omni
π
An Open-Source Omni-Model for Long Audio and Voice Clone
Running
on
Zero
9
OWSM V4 Demo
π
This is a demo for OWSM-V4 CTC and medium model.
Running
on
Zero
MCP
2
Chatterbox-Multilingual-TTS
π
Chatterbox TTS supporting 23 languages
Runtime error
221
Ebook2audiobook v25.8.18
π
Turn any ebook into audiobook, 1107+ languages supported!
Runtime error
10
VibeVoice 1.5B
π
Generate audio from text with AI voices
Running
on
Zero
7
Higgs-Audio Enhanced
π€
converts text into natural-sounding speech using AI.