Cohere Transcribe: Cohere's New Open-Source Speech-to-Text Model

Melvin Vivas · X video post · 2026-03-27 · 0:39 · 188 views · Open on X

Topics: Industry Trends & Job Market, LLM Fundamentals · Level: beginner

Summary

A short news post saying Cohere has released Cohere Transcribe, which it calls a new state-of-the-art open-source speech recognition (speech-to-text) model. The video has no spoken content (the transcript is only "Thank you."), so the lesson comes entirely from the caption. It's useful for knowing about this open-source ASR option when building voice features into AI apps.

Key points

• Cohere released Cohere Transcribe, an open-source speech-to-text (automatic speech recognition) model.
• Cohere's own announcement calls it a new state of the art in open-source speech recognition.
• Because it's open source, you can run it yourself instead of paying for a hosted transcription API.
• The post gives no benchmarks, languages, model size or setup steps. Check Cohere's official release for those details.
• The post was published on 2026-03-27. The video has no spoken explanation.

Resources mentioned

• Cohere Transcribe · tool · cohere.com · free
  Cohere's open-source speech recognition (speech-to-text) model, which Cohere bills as state of the art.
• Cohere · person · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  AI company that builds language, embedding and reranking models, and now the Transcribe speech-recognition model.
  Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Cohere Parse Beats Frontier LLMs at Receipt Parsing (Melvin Vivas on X · notes), Cohere Parse: Pricing vs Parse Bench Score (Melvin Vivas on X · notes), Cohere's North Micro Vision: a small open-source vision model for documents (Melvin Vivas on X · notes) and 1 more