IonBin
All pages
Search

Wispr Flow

Speech and voice AI
OpsBuild MCPAPI/CLIFile import

Independent review. Unpaid; no partnership with Wispr Flow. Based on public documentation and research. Trademarks identify their owners’ products. Disclosure.

Dictation that turns speech into edited text across supported apps, plus desktop meeting notes. Dictation types into an active app; a separate, read-only MCP server lets authorized AI clients retrieve Notetaker content.

The Ion perspective

The five-point review

Judgment, not a score. Documentation checked 2026-10-18.

Value
Dictation that turns speech into edited text across supported apps, plus desktop meeting notes. Dictation types into an active app; a separate, read-only MCP server lets authorized AI clients retrieve Notetaker content.
Differentiation
Documented fit: Talking through a detailed brief to an AI assistant; Fast replies and notes without typing; Retrieving permitted meeting notes through a separate AI connector. Uniqueness is not established.
Replaceability and switching
Compare Deepgram. Not drop-in replacements. Export completeness and migration effort remain unverified.
Ease and technical aptitude
Consider the fit limits: Shared or open-plan spaces; Regulated content without checking the vendor's data terms. Setup effort has not been scored.
Interoperability and portability
See documented MCP, API and import routes below. Import does not prove export; API access does not prove a complete migration path. Check action scope, plans and portability.

Connections: MCP connections · APIs · Portability and vendor lock-in.

Best for
  • Talking through a detailed brief to an AI assistant
  • Fast replies and notes without typing
  • Retrieving permitted meeting notes through a separate AI connector
Not for
  • Shared or open-plan spaces
  • Regulated content without checking the vendor's data terms

Top use cases

  • Talking through a detailed brief to an AI assistant
  • Fast replies and notes without typing
  • Retrieving permitted meeting notes through a separate AI connector

To verify Drawn from our draft verdict; sourced use cases to come.

In depth

Plans

US Pro costs $15/user monthly or $144 yearly. Free desktop dictation slows after its 2,000-word weekly allowance and stops at 5,000; mobile has separate lower limits. Growth and Enterprise offer additional administration; Notetaker inclusion depends on the selected package. Regional and app-store prices can differ. source ↗

Meeting access is separate from dictation

MCP authorization covers existing account content, not selected meetings. It is read-only and excludes dictation and Notetaker chat history. Organization policies and HIPAA agreements can block access. Search covers titles, summaries and notes; ask explicitly for a permitted transcript when needed. The app need not remain open for connected clients to read. source ↗

Imports upload meeting text

Granola CSV/ZIP and Otter transcript exports can be imported on desktop. Imports omit audio and calendar links. The import guide says these uploads sync to Wispr even when the Dictation cloud-storage switch is off; an active HIPAA agreement blocks syncing. Review the destination account and applicable data policy before importing. source ↗

How to use it with AI

How Wispr Flow connects to each AI platform: native connector or MCP, API through code the agent writes, browser control, or file upload.

PlatformMCP / connectorAPI (agent-written code)BrowserUpload / export
Claude (incl. Claude Code) Not documented Official help names this client for read-only meeting access. A named plugin, skill or CLI does not by itself establish an MCP/native connector pairing. Verify the route and client setup. Wispr Flow named integration docs ↗Claude (incl. Claude Code) MCP docs ↗ Not documented Claude (incl. Claude Code): Claude Code edits files and runs commands Wispr Flow publishes an API, but this pairing still needs network, authentication and execution-scope checks. Wispr Flow API ↗Claude (incl. Claude Code) docs ↗ No documented route Not documented Verify which side exports and which imports, supported formats and permissions. Wispr Flow's recorded upload/import status is yes; Claude (incl. Claude Code)'s file status is yes. These flags do not establish a file-transfer route. Wispr Flow file docs ↗Claude (incl. Claude Code) file docs ↗
OpenAI Codex Not documented Official help identifies Codex among OpenAI clients using the ChatGPT connection card. A named plugin, skill or CLI does not by itself establish an MCP/native connector pairing. Verify the route and client setup. Wispr Flow named integration docs ↗OpenAI Codex MCP docs ↗ Not documented OpenAI Codex: Edits files and runs commands locally; cloud tasks run in isolated workspaces Wispr Flow publishes an API, but this pairing still needs network, authentication and execution-scope checks. Wispr Flow API ↗OpenAI Codex docs ↗ No documented route Not documented Verify which side exports and which imports, supported formats and permissions. Wispr Flow's recorded upload/import status is yes; OpenAI Codex's file status is yes. These flags do not establish a file-transfer route. Wispr Flow file docs ↗OpenAI Codex file docs ↗
Google Antigravity Not documented Wispr Flow has an official MCP server and Google Antigravity supports MCP, but Wispr Flow's docs don't name this pairing. Auth setup may differ. Wispr Flow MCP docs ↗Google Antigravity MCP docs ↗ Not documented Google Antigravity: Agents edit code and run tasks Wispr Flow publishes an API, but this pairing still needs network, authentication and execution-scope checks. Wispr Flow API ↗Google Antigravity docs ↗ No documented route Not documented Verify which side exports and which imports, supported formats and permissions. Wispr Flow's recorded upload/import status is yes; Google Antigravity's file status is yes. These flags do not establish a file-transfer route. Wispr Flow file docs ↗Google Antigravity file docs ↗

Wispr Flow's docs also name: ChatGPT, Gemini.

Confirmed is reserved for evidence of the specific connection route. The current named integrations include plugins, skills and CLIs, so a named platform alone does not confirm MCP or a native connector. Inferred means each side documents a relevant capability, but no document describes the pairing. Code execution still needs network and credential access; file handling still needs a compatible format and transfer direction. Not documented means the records do not establish the route. IonBin has not tested these pairings. Recorded Oct 18, 2026.

Agent compatibility

MCPAPI/CLIFile import
LevelStatusDetail / source
Native connector / MCPYes Official docs ↗ — read-only Notetaker MCP on eligible Mac/Windows accounts; browser authorization and organization policies apply.
API / CLIYes Official docs ↗ — organization approval required before accessing developer API keys.
Browser / manualNo Browser access is not recorded for this tool.
File upload / importYes Official docs ↗ — desktop import of Granola/Otter export files; text only, not meeting audio.

Recorded Oct 18, 2026. Setup and plan limits vary; check the vendor's docs. How levels are assigned.

Appears in these proposed stacks

Connection capabilities to compare

An official MCP server is documented for this tool. These platforms separately document MCP client support: ChatGPT, Claude, Cursor, Gemini (Google), Google Antigravity, Grok, Grok Bot, Lindy, LM Studio, Mistral Vibe, OpenAI Codex. This inventory does not establish compatible transport, authentication or actions for a pairing. Check the connection matrix and linked sources.

Automation hubs to assess for a custom API connection: Gumloop, Make, n8n, Zapier. Verify credentials, supported requests, limits and error handling; no configured integration is implied.

Workflows using this tool

Explained in the wiki

Review

No long-form review yet. Verdict is based on research, not hands-on testing.

Alternatives

Deepgram

Speech and voice AI

Speech recognition and voice-agent APIs. Flux adds model-integrated end-of-turn detection for voice agents; Nova covers conventional streaming and batch transcription.

MCPAPI/CLIFile import
Build