Convert speech to text from audio files
Transcribe audio or YouTube videos into text
StyleTTS2 trained on ukrainian dataset
Convert text to speech effortlessly
Moonshine ASR models running on-device, in your web browser.
IndicParler_TTS for Urdu_Punjabi & Sindhi
Generate speech from text with custom voice
Spanish finetune for the original F5 model.
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Explore and analyze audio data with AudioBench Leaderboard
Belarusian TTS
Generate Vietnamese speech from text and reference audio
FunASR is an innovative Speech Synthesis tool designed to convert speech from audio files into text. It offers a seamless and efficient solution for transcription needs, catering to individuals, businesses, and developers alike. With state-of-the-art AI technology, FunASR ensures high accuracy and reliability in speech-to-text conversion.
• Multi-format support: Compatible with popular audio formats like MP3, WAV, and AAC.
• Real-time conversion: Quickly transcribe audio files with minimal processing time.
• High accuracy: Leveraging advanced AI models to deliver precise text outputs.
• Multi-language support: Transcribe speech in multiple languages for global accessibility.
• User-friendly interface: Simple and intuitive design for effortless usage.
What is the maximum file size supported by FunASR?
FunASR supports audio files up to 30 minutes in length for optimal performance.
Does FunASR support multiple speakers in an audio file?
Yes, FunASR is capable of identifying and labeling multiple speakers in a single audio file.
Is my data private when using FunASR?
Absolutely! FunASR ensures end-to-end encryption and compliance with data privacy standards to protect your files.
Can I use FunASR for real-time transcription during live events?
Yes, FunASR supports real-time transcription, making it ideal for live events, meetings, and interviews.