AI use case

Cohere Open Source Voice Model for Transcription

Cohere has launched an open source voice model specifically designed for transcription, with just 2 billion parameters, meant for use with consumer-grade GPUs for self-hosting, …

Browse catalog

At a glance

Core facts from this catalog record. Primary narrative lives in the hero above; full raw fields follow in the next section.

Company/Organization: Cohere
Industry: Internet Software & Services
Location: Toronto

Record fields

Every column from the source row, in stable order. URLs open in a new tab.

Title

Cohere Open Source Voice Model for Transcription

Content

Cohere launches an open source voice model specifically for transcription. Relatively light at just 2 billion parameters, the model is meant for use with consumer-grade GPUs for those who want to self-host it. It currently supports 14 languages. The model lets enterprises build voice agents for sales and customer engagement, putting Cohere in direct competition with the likes of ElevenLabs, Deepgram, and OpenAI. This open source release enables developers and businesses to deploy high-quality speech-to-text capabilities on their own infrastructure.

URL

https://techcrunch.com/2026/03/26/cohere-launches-an-open-source-voice-model-specifically-for-transcription/

City

Continue exploring AI deployments in the catalog.

Back to use cases