Tonic Textual

What it does

Tonic Textual is AI-powered software for de-identifying unstructured data, including free text, documents, spreadsheets, scanned forms, and audio. It uses named-entity recognition models to find sensitive information, with an LLM check described as filtering false positives. Users can redact detected values or replace them with realistic synthetic values; replacements can remain consistent across files, helping preserve references for training, analysis, testing, or sharing.

The product is aimed at AI, data, and development teams handling sensitive text, including healthcare teams working with clinical notes. Data can be provided through the user interface, Python SDK, or API. Textual is available as a Tonic-hosted cloud service or self-hosted with Kubernetes or Docker, and can connect to Amazon S3, Google Cloud Storage, and Azure Blob Storage. Textual Agent also supports plain-language configuration and a choice of model provider. Textual pricing is usage-based on words processed; the published page does not state a numeric rate and directs buyers to request a quote.

What it can do

• Detects sensitive information in text and files using proprietary named-entity recognition models
• Redacts sensitive values or replaces them with synthetic values
• Maintains consistent synthetic replacements across files in a dataset
• Supports custom entity types trained on examples from a team's data
• Processes documents, scanned forms, spreadsheets, and audio
• Offers plain-language configuration through Textual Agent

Works with

• Amazon S3
• Google Cloud Storage
• Azure Blob Storage
• Python SDK
• REST API
• Claude Code
• Gemini CLI
• OpenCode

Before you choose

• Textual pricing is volume-based on words processed; the pricing page gives no numeric rate and requires a custom quote.
• Self-hosting requires Kubernetes or Docker; no operating-system support details are supplied.
• The product describes detection and de-identification capabilities, but does not establish that every dataset will be free of sensitive information.

Listed under

• Data
• Data extraction
• Compliance
• Data-privacy
• Data-security
• De-identification
• LLM
• Pii-redaction

Get started

The Textual pricing route is word-volume based and directs users to request a custom quote.

1. Choose Tonic-hosted cloud or a self-hosted Kubernetes or Docker deployment.
2. Provide data through the UI, Python SDK, or API, or connect a supported cloud storage service.
3. Configure detection and select redaction or synthetic replacement; contact Tonic for pricing.

The pricing page does not publish a numeric rate. It describes word-volume billing, with a custom quote; annual engagements may allocate a bank of words for use throughout the year.

Source: tonic.ai/pricing, checked 1 Nov 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 1 Nov 2026. Each source supports part of the overview; availability and prices can change.

• Tonic Textual | Unstructured Data De-Identification ↗www.tonic.ai
• Pricing | Tonic.ai | Synthetic Data Platform ↗www.tonic.ai
• Tonic.ai: Synthetic Data for Software and AI Development ↗www.tonic.ai
• Company Data De-Identification | Solutions | Tonic.ai ↗www.tonic.ai
• Contact | Tonic.ai ↗www.tonic.ai
• Product Documentation for the Tonic.ai Product Suite ↗www.tonic.ai

Company website

tonic.ai: product, pricing and policy pages

YC directory mirror

Batch and company name

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

manual_review

Last checked 1 Nov 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.