Canary 1B v2 is an open-source multitask model for automatic speech recognition and translation, supporting 25 languages. It enables developers to transcribe and translate audio to text using local inference or integration with tools like transcribe.cpp. The model is suitable for building multilingual ASR and translation applications.
Canary 1b is a Voice, TTS & speech product. It focuses on transcribing and translating speech to text across multiple languages using an open-source model. It is built as an open-source project for developers building speech recognition or translation applications. Canary 1b is open source under the MIT license. The product ships for the web, the command line, and API, and it can be self-hosted.
Behind Canary 1b is Memoravox, and the product first shipped in 2026. Development happens publicly on GitHub with 176 stars and 458 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Canary 1b occupies a relatively distinct niche. Key capabilities include speech transcription, multilingual support, and speech-to-text.
Latest indexed changes and source events
memoravox/canary-1b-v2-gguf discovered by the PulseGate indexer
Other apps tracked under the same category.
