Picovoice is the first and only ubiquitous on-device voice AI platform. Its stack can run on anything from embedded devices to web browsers. Picovoice offers Speech-to-Text, Streaming Speech-to-Text, Noise Suppression and Cancellation, Speech-to-Index (Phrase Search), Wake Word, Speech-to-Intent, and Voice Activity Detection engines.
No features have been listed yet.
I cannot believe I haven't met Picovoice before. The free plan is decent to get familiar with the tech and the tech is sick. I mean it. I tried Amazon, Microsoft, Google, Deepgram, Assembly and Speechmatics. I thought Deepgram was fast. You get Speaker Recognition, Noise Suppression and Voice Activity Detection and all the other stuff too.
AssemblyAI - Robust and Accurate Multilingual Speech Recognition
Express Scribe - Express Scribe transcription software and audio player specifically designed for typists.
RunLve - Accelerate growth efficiently for everyone with the AI and data science experts.
Kaldi - Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0.
Azure Speech Services - Learn more about Cognitive Speech Services, a comprehensive new offering that includes text to speech, speech to text and speech translation capabilities. Demo speech services today.
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.