Whisper vs Distil-Whisper
📈
71
Audio Spaces
-
-
Seamless M4T
📞949 -
MusicGen
🎵5.07kGenerate music from text descriptions and optional melodies
-
Audioldm Text To Audio Generation
🔊815Generate audio from text descriptions
-
AudioLDM2 Text2Audio Text2Music Generation
🔊307Generate audio and waveform video from text
-
AudioSep
🐠222 -
Lp Music Caps
🎵172Generate captions for music audio
-
Tortoise Tts
🐢315ExpressivText-to-Speech
-
All In One
📊22 -
XTTS
🐸2.77kGenerate speech from text using a reference voice
-
Coqui Bark Voice Cloning
🐸189 -
VALL E X
🎙365Generate audio from text using voice prompts
-
WavJourney
🔥193 -
Music To Image
🎶263 -
MMS
🌍277Transform and identify speech with MMS
-
ElevenLabs TTS
🗣620Generate spoken audio from text using selectable voices
-
AudioGPT
🚀288 -
Bark
🐶2.37kGenerate realistic audio from text
-
SpeechT5 Speech Recognition Demo
👩37 -
CoquiTTS (Official)
🐸172 -
Whisper
📉2.76kTranscribe audio files into text
-
Moe TTS
😊667Generate and convert voice using text and audio inputs
-
YourTTS
🔥17 -
Talking Face Generation with Multilingual TTS
👄560Generate multilingual talking-face videos from your text
-
OpenAI TTS New
📊560 -
Mustango
🐢166 -
OWSM Demo
🔊55 -
StyleTTS 2
🗣725Efficient, fast, and natural text to speech with StyleTTS 2!
-
HierSpeech++ (Zero-shot TTS)
⚡396Generate high-quality speech from text using a prompt audio
-
Video2music
📚21Generate music for a video based on its content and key
-
Whisper Large V2
🤫187 -
Musicgen Prompt Upsampling
🌖64Generate music from text prompts 🎶
-
Seamless M4T v2
📞516Translate speech and text between languages
-
Seamless Streaming
📞326Translate text between languages
-
Matcha TTS
🍵53Generate speech from text with speaker selection
-
MusicGen Streaming
🔥293Generate music from text descriptions in real-time
-
Resemble Enhance
🚀459Enhance and denoise your audio files
-
Singing Voice Conversion
🎼262Transform your voice into a singer's
-
NaturalSpeech2
🎧52Generate speech with cloned timbre
-
Create Your Own TTS Dataset
🔥22 -
Podcast Transcription
🐢 -
OpenVoice
🤗1.13kGenerate speech in a cloned voice from a short audio sample
-
M2UGen Demo
💻94 -
Pheme
📊68 -
ESPnet2 TTS
📈6Convert text to speech in English, Chinese, or Japanese
-
Whisper-WebUI
🚀41Generate subtitles and translate audio files
-
Image2SFX Comparison
👂177Generates audio environment from an image
-
WhisperSpeech
🌬379 -
MetaVoice 1B
🗣144A demo of MetaVoice 1B, a new TTS model by MetaVoice.
-
TTS Arena V2
🏆943Vote on the latest TTS models!
-
Whisper Speech X DreamTalk
😽179Combine voice cloning and portrait lipsync animation
-
Canary 1b
🐤197Transcribe and translate audio into text
-
SALMONN Audio Questioning
⚡83Deeply interrogate audio file content
-
MeloTTS
🗣473Fast, efficient, & multilingual text-to-speech
-
Audio Editing
🎧327Edit audios with text prompts
-
ChatMusician
💻18 -
xVASynth TTS
🧝73CPU powered, low RTF, emotional, multilingual TTS
-
NaturalSpeech3 FACodec
🏃178Convert and reconstruct speech files
-
Hey Gemma
☎25 -
Ratchet + Whisper
🗣70Convert audio to text
-
AutoSubs
📜3Automatically add on-screen subs to your videos
-
VoiceCraft
📈161 -
TangoFlux
🚀325Text to Audio (Sound SFX) Generator
-
Parler-TTS
🥖846High-fidelity Text-To-Speech
-
Sing an idea ➡️ Music
🔥184Bring song ideas to life
-
Musicgen Songstarter Demo
👁75Generate music using descriptions and optional melody audio
-
Whisper JAX
👀145Transcribe or translate audio from microphone, file, or YouTube
-
AudioLCM
🏢23Generate audio from text
-
Stable Audio Live Multiplayer
💻163Generate custom audio from text prompts
-
Stable Audio Open Zero
🔥464Generate immersive audio from text prompts
-
Make An Audio 3
🐠14Generate audio from text prompts
-
Mars5 Space
📉60 -
Tango Music AF
🎵5Text to Music Generator
-
Jam
🐠16Generate a song from lyrics and style reference
-
BigVGAN
🔊114Generate high‑quality audio from your input file with BigVGAN
-
SenseVoice
🐠90Transcribe audio with emotions and events
-
PicoAudio
📈27Generate audio from text descriptions with timestamps
-
Audio Flamingo Demo
📚7 -
MusiConGen
🪩29 -
Mms Zeroshot
🌍20Transcribe audio in any language using text data
-
GPT SoVITS V2 Pro Plus
🤗230Generate speech from text using a reference voice
-
EzAudio
🟣275Generate or edit realistic audio from text prompts
-
OpenMusic
🎶214Generate music from text descriptions
-
Midi Music Generator
🎼572Generate MIDI music from prompts
-
Whisper Turbo
🤯1.01kTranscribe or translate audio and YouTube videos to text
-
Realtime Whisper Turbo
🤯346Realtime implementation of Whisper large turbo
-
Whisper Large V3 Turbo WebGPU
🚀170ML-powered speech recognition directly in your browser
-
Fish Audio S1
🏆696Convert text to natural-sounding speech audio
-
TTS Spaces Arena
🤗479Blind vote on HF TTS models!
-
Diva Realtime Chat
🗣19Generate text responses from audio input
-
F5-TTS
🗣2.84kF5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
-
MaskGCT TTS Demo
😻259MaskGCT TTS Demo
-
MelodyFlow
🎵159Generate or edit music from text and optional audio
-
Fish Agent
💬148An end-to-end (e2e) Voice Language Model by Fish Audio.
-
Nexa Omni Demo
🎧66Generate text from uploaded or recorded audio
-
Kokoro TTS
❤3.26kUpgraded to v1.0!
-
Make Custom Voices With KokoroTTS
⚡133Make Custom Voices With KokoroTTS
-
Llasa 3b Tts
🔥313Zero Shot voice cloning with llasa 3b (Unofficial Demo)
-
Llasa 1b Multilingual TTS
🌍12Generate speech from text with or without cloning a voice
-
Kokoro Text-to-Speech (WebGPU)
🗣354High-quality speech synthesis powered by Kokoro TTS
-
Hibiki Simple
👄42High-Fidelity Simultaneous Speech-To-Speech Translation
-
Zonos
🌍413Generate expressive speech audio from text with custom voice
-
Kokoro Web
🗣82ML-powered speech synthesis directly in your browser
-
Di♪♪Rhythm
🎶684Blazingly Fast and Embarrassingly Simple Song Generation
-
Audiobox Aesthetics
📚23Demo for audiobox-aesthetics
-
Spark TTS
🌖229A text-to-speech model powered by SparkAudio and Mobvoi.
-
Sesame CSM
🌱862Conversational speech generation
-
Orpheus TTS
🚀246Try Orpheus TTS here
-
Canary 1B Flash
🐤43Canary 1B Flash demo
-
IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
🎙216Generate speech from text using a reference audio
-
AudioMorphix
🌊6Prepare environment and run Gradio app
-
MegaTTS3 Demo
👋93 -
AudioX
👀166Generate audio from text, video, or audio prompts
-
Vevo for Zero-shot VC, TTS, and More
🐠100Controllable Zero-Shot Voice Imitation
-
Dia 1.6B
👯1.76kGenerate realistic dialogue from a script, using Dia!
-
Aero 1 Audio Demo
💬43Demo for Aero-1-Audio
-
Voila Demo
💻44Chat with a voice-clone AI
-
ACE Step
😻654A Step Towards Music Generation Foundation Model
-
Audio Difficulty Estimator
🎹2Estimate piano difficulty from audio
-
TIGER Audio Extractor
✂113Extraction & Reconstruction for Efficient Speech Separation
-
Music2emo
📊18Towards Unified Music Emotion Recognition across Dimensional
-
SonicVerse
🖼13Generate detailed music descriptions from audio clips
-
Auffusion
😻44Audio Gen, Audio Style Transfer and Audio InPainting
-
Chatterbox TTS
🍿1.73kExpressive Zeroshot TTS
-
PlayDiffusion
🎨119Generate modified audio from text and voice
-
Voice Clone Arena
🏆2Vote on the latest Voice Clone TTS models!
-
Conversational WebGPU
🚀233 -
Song Generation
🎵697Generate a song from your lyrics and description
-
NotaGen
📊72Generate classical sheet music in ABC notation
-
Audio Flamingo 3 Demo
🚀100Audio Flamingo 3 Demo
-
Audio Flamingo 3 Chat
🐠33Audio Flamingo 3 demo for multi-turn multi-audio chat
-
MSR UTMOS
🐢6Multiple sampling rate MOS prediction with SFI conv
-
Higgs Audio Demo
🎤398Higgs Audio Demo
-
sidon_demo_beta
🐋27Speech restoration demo of Sidon.
-
Canary 1b V2
🐤68Transcribe and Translate in 25 European Languages
-
SonicMaster – Text-Guided Music Restoration & Mastering
🎧28Enhance audio quality using text prompts
-
OLMoASR
🌍6Open Models and Data for Training Robust Speech Recognition
-
VibeVoice-Large
🏃85Generate a podcast audio from a script and voice samples
-
TaDiCodec TTS AR Qwen2.5 0.5B
📚10Generate speech from text with voice cloning
-
EchoX
🔥8An end-to-end speech large language model.
-
VoxCPM 0.5B
🐢44Generate expressive speech from text with optional voice cloning
-
FireRedTTS2
🔥34Long-form multi-speaker dialogue generation
-
FireRedASR
🚀12FireRedASR Demo
-
IndexTTS 2 Demo
🏢782Generate expressive speech audio from text with emotion control
-
SongFormer
🎵20State-of-the-art music analysis with multi-scale datasets
-
Voice Acting TTS
🎭26TTS for any emotion, now with non-verbal sounds!
-
Omnilingual ASR Media Transcription
🌍238Transcribe audio/video files into text instantly
-
Music Flamingo
🎵161Ask questions about any song and get detailed answers
-
Maya1
📉118Demo of our new open source model maya1
-
Supertonic (TTS)
⚡217Lightning-Fast, On-Device TTS
-
Dia2 2B
💨74Streaming conversational audio in realtime
-
VibeVoice-Realtime-0.5B
🐨181Generate natural speech from text with selectable voices
-
Count The Notes
🎵1Convert audio to MIDI
-
SpeechJudge GRM
📈1Evaluate naturalness of two audio files
-
Chatterbox Turbo Demo
⚡489Chatterbox Turbo Demo
-
Soprano TTS
🗣147Now with upgraded v1.1 model!
-
Qwen3-TTS Demo
🎙1.81kGenerate speech from text with custom voice, cloning, or presets
-
Qwen3-ASR Demo
🎙121Transcribe audio to text with multi-language timestamps
-
Voxtral Mini Realtime
🎤155Transcribe speech to text instantly in real time
-
ACE-Step v1.5
🎵466Music Generation Foundation Model v1.5
-
Parakeet STT Progressive Transcription
🎤88Transcribe speech to text instantly with WebGPU acceleration
-
faster-qwen3-tts
🎙205Generate speech audio from text with custom or cloned voices
-
Fish Audio S2 Pro
🐟133Zero GPU Text-to-Speech using Fish Audio S2 Pro
-
TADA
🎵85Generate speech that mimics a given voice from text
-
Voxtral Realtime WebGPU
💬100Real-time speech transcription, entirely in your browser.
-
TADA — Text-Acoustic Dual Alignment for Speech
🗯22Speech generation from text and acoustic reference
-
Foundation 1
🚀60Generate custom music clips from text prompts
-
LongCat AudioDiT 3.5B
🐱6Generate speech from text or clone a voice using a sample