Typestream

Provides a developer API for speech-to-text and voice dictation that converts spoken audio into accurate text to reduce typing friction and enable voice-driven input, search, and AI interactions. Sells to software developers and product and engineering teams at B2B software and app companies that want to add voice features. Delivered as a pay-as-you-go, API-first service with ephemeral audio processing, prebuilt UI components, and multi-language SDKs that integrates with a few lines of code.

Key features

• Speech-to-text voice dictation API
• Ephemeral audio processing with immediate purge
• Prebuilt UI components with SSR support
• API key creation and revocation dashboard
• Multi-language SDKs for frontend and backend
• OpenAPI and MCP Server support
• AI-agent ready integration via skills.md
• Chrome extension for dictation in any tab
• Hotkey talk-then-send with clipboard fallback