alytts
Generate speech from text using OpenAI API
Generate speech from text using OpenAI API
Text-to-Speech, Speech-to-Text, and Language Recognition
Clone a voice using a text and audio sample
Generate audio from text using pre-trained models
Create custom voice clones using text input
Create interactive music playlists with AI assistance
Generate audio effects from video using image caption
Generate voice from text with customizable audio source
A demo of MetaVoice 1B, a new TTS model by MetaVoice.
Convert text to speech
Run a web-based application
Convert audio to text
Convert voice to another voice
Generate or edit spoken audio from text
High-fidelity Text-To-Speech
Languages ru,en,zh-cn,ja,de,fr,it,pt,pl,tr,ko,nl,cs,ar,es,hu
Generate music powered by AI
Convert voice to text
Generate audio by cloning a voice
Generate speech from text using ElevenLabs voices
Generate speech in a cloned voice
Generate custom audio clips from text prompts
Transcribe or translate audio files
Generate speech from text
Transcribe audio to text with speaker diarization
Generate speech from text using various voices
easy download youtube audios with gradio
Transform a report or document into an interview/discussion
Convert text to audio and vice versa
Generate music from text descriptions
Convert audio to text with ease and accuracy.
Restore degraded audio using a Transformer-based model
Generate audio from text using selected characters
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Whisper Transcribe MP3 files, use a GPU to convert faster!
Vocal and background audio separator
Audio-Driven Portrait Animations
Fixed fork of the original audio sr!
Generate speech from text with or without voice cloning
Convert text to natural-sounding speech audio
WebGPU text-to-Speech powered by OuteTTS and Transformers.js
Transform audio into text using a web-based model
Real-time in-browser speech recognition
High-quality speech synthesis powered by Kokoro TTS
Translate and synthesize speech to English
Make Custom Voices With KokoroTTS
Zero Shot voice cloning with llasa 3b (Unofficial Demo)
Analyze music to identify genre, instrument, mood, and more
Generate Podcast using Kokoro-TTS!
Blazingly Fast and Embarrassingly Simple Song Generation
Conversational speech generation
Chat with an AI using text, audio, image, or video and hear responses
Generate audio from text, video, or audio prompts
SText to Audio(Sound SFX) Generator
Demo for OpenF5-TTS
A Step Towards Music Generation Foundation Model
Expressive Zeroshot TTS
Extraction & Reconstruction for Efficient Speech Separation
Generate speech from text using various TTS services
Generate custom songs from lyrics and prompts
Generate a waveform video from an audio file
Generate speech from text with customizable voice and speed
Audio Flamingo 3 Demo
Audio Flamingo 3 demo for multi-turn multi-audio chat
Generate speech from text with selectable voice
Demo space for Mistral latest speech models
Search audio for relevant chunks
Higgs Audio Demo
State-of-the-art audio transcription in your browser
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Conversational speech generation
State-of-the-art TTS model under 25MB
Audio Gen, Audio Style Transfer and Audio InPainting
Transcribe uploaded audio to text with language detection
Generate natural speech from text with many voices
Translate speech live with text and audio output
Generate captions from audio
Clone a voice to speak new text
Free Text-To-Speech generator with Emotion control (OpenAI)
Generate expressive speech from text using various models
Demo of our new open source model maya1
CPU - Gradio. Old smol TTS champ. 54 voices.
New smol king for speech generation
Simple Whisper-Large-V3-Turbo running on CPU/CUDA for local
Chatterbox Turbo Demo
Now with upgraded v1.1 model!
Local 32kHz High-Fidelity TTS, optimized for speed.
Local whisper but for current year
Generate custom voice audio from text and description
An incredibly fast and tiny audio upsampler
Generate speech from text with voice design, cloning, or speakers
Space for LuxTTS: a 150x realtime voice cloning TTS model
Generate speech with voice cloning from reference audio