The request names Deepgram, so Deepgram comes first: its page describes Speech-to-Text, Text-to-Speech and Voice Agent APIs and includes a batch POST /v2/speak example for comparing TTS voices side by side 1. Its indexed actions cover project keys, usage and project settings rather than SDK patterns 11. Alternatives that do voice or audio agent work are LiveKit, for building voice agents with its Agents SDK 20, and the AI SDK, for streaming multi-model AI apps in TypeScript 717.
- 1
Deepgramdeepgram.comverified and signed
Provides Speech-to-Text, Text-to-Speech and Voice Agent APIs, including batch POST /v2/speak for synthesizing a script in several voices 1, and its indexed actions list project keys, usage breakdowns and project settings 11.
+6 community tools built for it
for agents: list_project_keys · get_usage · get_project
- 2
- 3
AI SDKai-sdk.devverified and signed
A unified TypeScript SDK for building AI apps with streaming and multi-model support, usable for wiring voice or speech models into app code 717.
official:MCP server · @ai-sdk/mcpSDK · aiskill · ai-sdkskill · Skillsskill · building-components
for agents: sdk · ai-sdk · flags-sdk
Sources
- 1Enterprise voice AI: STT, TTS & agent APIs | Deepgramdeepgram.com · read 2026-10-29
- 7AI SDKai-sdk.dev · read 2026-10-29
- 10Build voice, video, and physical AI | LiveKitlivekit.com · read 2026-10-29
- 11Deepgram (Activepieces): declares "list_project_keys" (the record we read and signed)unfragile.ai · read 2026-10-24
- 17ai: declares "sdk" (the record we read and signed)unfragile.ai · read 2026-10-24
- 20livekit-agents: declares "livekit-agents" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
list_project_keys · Deepgram (Activepieces) verified and signed
List API Keys — Lists the API keys of a Deepgram project (never the secret values). A member key only sees its own keys.
dataverse-python-advanced-patterns · dataverse-python-advanced-patterns verified and signed
Generate production code for Dataverse SDK using advanced patterns, error handling, and optimization techniques.
vercel-composition-patterns · vercel-composition-patterns verified and signed
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 AP
createEdgeConfig · Vercel API verified and signed
Create an Edge Config
sentry-sdk-skill-creator · sentry-sdk-skill-creator verified and signed
Create a complete Sentry SDK skill bundle for any platform. Use when asked to "create an SDK skill", "add a new platform skill", "write a Sentry skill for X", or build a new sentry-<platform>-sdk skill bundle with wizard flow and feature reference files.
dsql · dsql verified and signed
Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.
sdk · ai verified and signed
deep-agents-memory · deep-agents-memory verified and signed
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
mongodb-schema-design · mongodb-schema-design verified and signed
MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on "design schema", "embed vs reference", "MongoDB data model", "schema review", "unbounded arrays", "one
livekit-agents · livekit-agents verified and signed
Build voice AI agents with LiveKit Cloud and the Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Provides opinionated guidance for the recommended path: Li
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.