A transcript from a Tuesday morning earnings call arrives as plain text inside a US bank’s data center, and nine seconds later, a summary, a sentiment score, and three flagged sentences are in a portfolio manager’s inbox. The US market for NLP in finance reached $6.9 billion in 2025 according to Market.us research, more than double its 2021 value, with 58% of US banks running NLP inside compliance workflows by 2026. An NLP system in finance has four stages: ingest, process, decide, and serve. Ingest pulls text from sources like SEC filings, earnings call transcripts, news wires, internal emails, customer chats, and operational logs. Process turns raw text into tokenized, normalized, embedded vector space. Decide classifies, scores, summarizes, or extracts entities. Serve delivers output to a trading desk dashboard, compliance review queue, or customer support agent screen. Most US banks retrofit NLP into existing case management and risk systems. JPMorgan Chase has described its COiN platform, which automated review of commercial loan agreements that previously took 360,000 hours of legal review time a year. Citi has documented NLP use across credit memo generation and anti-money laundering case triage. For smaller institutions, the integration model is API-first. US banks in 2026 generally maintain three tiers of models, including small transformer models with 1 to 7 billion parameters.