IonBin
All pages
Search

Synthesia

AI video
Content MCPAPI/CLIFile import

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

Creates presenter-style videos with AI avatars and voices from a script. Its MCP server (public beta) and API let an AI assistant turn a script it wrote into a video draft.

The Ion perspective

The five-point review

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

Value
Creates presenter-style videos with AI avatars and voices from a script. Its MCP server (public beta) and API let an AI assistant turn a script it wrote into a video draft.
Differentiation
Documented fit: Training, explainer and product videos without filming. Uniqueness is not established.
Replaceability and switching
Compare HeyGen, PlayPlay, Descript. Not drop-in replacements. Export completeness and migration effort remain unverified.
Ease and technical aptitude
Consider the fit limits: Teams that can't use a beta integration (Synthesia's MCP is in public beta). 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
  • Training, explainer and product videos without filming
Not for
  • Teams that can't use a beta integration (Synthesia's MCP is in public beta)

Top use cases

  • Turn a script or idea into a Synthesia video draft from Claude or ChatGPT source ↗
  • Create a video from a template through the API source ↗
  • Generate personalized videos from a spreadsheet on Pro or Enterprise source ↗

In depth

Plans

Basic is free with watermarked videos and a monthly allowance. Monthly USD prices are $29 for Starter and $89 for entry Pro. Shared credits cover different features, so video minutes are estimates. Annual checkout totals were not verified. Bulk personalization and the Video API require Pro or Enterprise; MCP starts at Starter. source ↗

What the connector can change

The beta MCP supports Claude and ChatGPT with per-user, single-workspace access. It creates Studio drafts and renders final videos, but scene or narration edits to Studio drafts still need the editor. Syren videos can be edited in chat and consume credits. Enterprise SSO accounts on legacy Cognito must migrate to WorkOS. Review permissions and credit usage before generating. source ↗

How to use it with AI

How Synthesia 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 Named in Synthesia's MCP docs. A named plugin, skill or CLI does not by itself establish an MCP/native connector pairing. Verify the route and client setup. Synthesia named integration docs ↗Claude (incl. Claude Code) MCP docs ↗ Not documented Claude (incl. Claude Code): Claude Code edits files and runs commands Synthesia publishes an API, but this pairing still needs network, authentication and execution-scope checks. Synthesia API ↗Claude (incl. Claude Code) docs ↗ Inferred Claude Code with the Claude in Chrome extension (Chrome, Edge and other Chromium browsers). Synthesia is a web app; the pairing itself is not documented. Claude (incl. Claude Code) browser docs ↗ Not documented Verify which side exports and which imports, supported formats and permissions. Synthesia'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. Synthesia file docs ↗Claude (incl. Claude Code) file docs ↗
OpenAI Codex Not documented Synthesia has an official MCP server and OpenAI Codex supports MCP, but Synthesia's docs don't name this pairing. Auth setup may differ. Synthesia MCP docs ↗OpenAI Codex MCP docs ↗ Not documented OpenAI Codex: Edits files and runs commands locally; cloud tasks run in isolated workspaces Synthesia publishes an API, but this pairing still needs network, authentication and execution-scope checks. Synthesia API ↗OpenAI Codex docs ↗ Inferred Only in the ChatGPT desktop app; not in the Codex CLI or IDE extension. Synthesia is a web app; the pairing itself is not documented. OpenAI Codex browser docs ↗ Not documented Verify which side exports and which imports, supported formats and permissions. Synthesia's recorded upload/import status is yes; OpenAI Codex's file status is yes. These flags do not establish a file-transfer route. Synthesia file docs ↗OpenAI Codex file docs ↗
Google Antigravity Not documented Synthesia has an official MCP server and Google Antigravity supports MCP, but Synthesia's docs don't name this pairing. Auth setup may differ. Synthesia MCP docs ↗Google Antigravity MCP docs ↗ Not documented Google Antigravity: Agents edit code and run tasks Synthesia publishes an API, but this pairing still needs network, authentication and execution-scope checks. Synthesia API ↗Google Antigravity docs ↗ Inferred The /browser guide documents App and CLI support through Chrome DevTools MCP; the overview comparison conflicts on CLI availability. IDE browser features are separate. Synthesia is a web app; the pairing itself is not documented. Google Antigravity browser docs ↗ Not documented Verify which side exports and which imports, supported formats and permissions. Synthesia's recorded upload/import status is yes; Google Antigravity's file status is yes. These flags do not establish a file-transfer route. Synthesia file docs ↗Google Antigravity file docs ↗

Synthesia's docs also name: ChatGPT.

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 ↗ — public beta; Starter, Pro or eligible Enterprise workspace; WorkOS OAuth and client/admin permissions required.
API / CLIYes Official docs ↗ — Video API requires Pro or above; other APIs have separate eligibility.
Browser / manualNo Browser access is recorded alongside a documented programmatic route.
File upload / importYes Official docs ↗ — CSV/XLSX template-variable import; bulk personalization requires Pro or Enterprise.

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

Review

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

Alternatives

HeyGen

AI video

AI avatar video, AI video generation and video translation with editable translation scripts. A hosted MCP server (OAuth, no API key) lets AI agents create videos, billed against the HeyGen plan's credits.

MCPAPI/CLIFile import
Content

PlayPlay

AI video

Browser-based video creation for marketing and communications teams: script help, voice-over, subtitles in 120+ languages, subtitle translation into 40+ languages, and avatars. AI output is editable before sharing.

BrowserFile import
Content

Descript

Video editing

Edits video and podcasts by editing the transcript. Its MCP server and API let an AI assistant import media, edit projects and export transcripts; imports use media minutes and AI edits use AI credits.

MCPAPI/CLIFile import
Content