SpeechPulse converts your speech to text in real time using Whisper language models. It can type into your favorite apps, including text editors, web browsers, and office applications. SpeechPulse can also transcribe audio/video files. Most audio/video file types, including mp3, mp4, WAV, m4a, FLAC, Ogg, and WebM, are supported. It can also generate SRT and VTT subtitles for audio/video files with accurate timestamps. SpeechPulse can recognize speech in a variety of languages, including English, French, Spanish, Italian, German, Japanese, Chinese, and Russian. To provide best-in-class accuracy, SpeechPulse uses Whisper speech-to-text models. It has excellent accuracy even in noisy environments. SpeechPulse can also take advantage of your multi-core CPU or GPU to accelerate recognition. SpeechPulse is completely offline and does not require internet access.
