Wispr Flow - Don’t type, just speak
Mini toolsVoyage lite 01 instruct
By Voyage AI
voyage-lite-01-instruct is a text embedding model built on top of voyage-lite-01 and instruction-tuned specifically for classification and clustering tasks. It shares the same architecture as voyage-lite-01 with a context length of 4096 tokens and 1024-dimensional embedding vectors. The model produces representations optimized for classification and semantic clustering, and Voyage AI explicitly states these are the only recommended use cases, distinguishing it from the retrieval-focused voyage-01 and voyage-lite-01 models. It is accessible via the Voyage AI API and also available as open weights on Hugging Face under an MIT license. It is part of Voyage AI's first-generation model lineup and is now a legacy model, superseded by newer generations in the voyage-3 and voyage-4 families.
Text
Gen 7
Overview
Lightweight text embedding model fine-tuned on top of voyage-lite-01 for classification and clustering tasks. Features a 4096-token context window and 1024-dimensional output vectors. Not recommended for retrieval or search; classification and clustering are the only recommended use cases.
About Voyage AI
Voyage AI provides best-in-class embedding models and rerankers for search and retrieval over unstructured data, used to power retrieval-augmented generation (RAG) and AI applications. It offers general-purpose, domain-specific (finance, legal, code) and company-specific fine-tuned models. Founded in 2023 and based in Palo Alto, the company was acquired by MongoDB, Inc. in February 2025 and now operates as a MongoDB subsidiary.
View Company Profile
Last updated: June 23, 2026
