Convert text to speech using the configured TTS engine (Chatterbox Turbo or Kokoro). For Chatterbox Turbo, use paralinguistic tags directly in text for expressive speech: [laugh], [sigh], [cough], [chuckle], [gasp], [groan], [clear throat], [sniff], [shush]. Supports voice cloning via reference a...
Part of the Local Voice MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call synthesize_text to permanently remove or destroy resources in Local Voice. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call synthesize_text in a loop, permanently destroying resources in Local Voice. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
synthesize_text:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Local Voice policy for all 3 tools.
Agents calling destructive-class tools like synthesize_text have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
synthesize_text is one of the critical-risk operations in Local Voice. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Convert text to speech using the configured TTS engine (Chatterbox Turbo or Kokoro). For Chatterbox Turbo, use paralinguistic tags directly in text for expressive speech: [laugh], [sigh], [cough], [chuckle], [gasp], [groan], [clear throat], [sniff], [shush]. Supports voice cloning via reference audio.. It is categorised as a Destructive tool in the Local Voice MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for synthesize_text. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Local Voice MCP server.
synthesize_text is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the synthesize_text rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for synthesize_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
synthesize_text is provided by the Local Voice MCP server (@codecraftersllc/local-voice-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept