VX Agents

OpenAPI Marketplace

Amazon Transcribe and Polly

v1.0.0 · 2 endpoints · 0 connections · shared by vx.ai

Official AWS REST operations for speech transcription and speech synthesis.

Connect this API to an AI agent Browse all specs

What you can do with Amazon Transcribe and Polly via MCP

Every endpoint below becomes a governed tool your AI agent (Claude, ChatGPT, or a customer-facing VX agent) can call — with scoped permissions, sandbox testing, and audit logs.

MethodPathOperationDescription
POST / startTranscriptionJob Start transcription job Method: POST Path: / IMPORTANT: This function has 3 REQUIRED parameter(s) and 4 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Header Parameters: REQUIRED: - X-Amz-Target: No description Request Body: REQUIRED: - TranscriptionJobName: TranscriptionJobName parameter from application/json - Media: Media parameter from application/json OPTIONAL: - LanguageCode: LanguageCode parameter from application/json - IdentifyLanguage: IdentifyLanguage parameter from application/json - IdentifyMultipleLanguages: IdentifyMultipleLanguages parameter from application/json - MediaFormat: MediaFormat parameter from application/json
POST /v1/speech synthesizeSpeech Synthesize speech Method: POST Path: /v1/speech IMPORTANT: This function has 3 REQUIRED parameter(s) and 4 OPTIONAL parameter(s) REQUIRED parameters MUST be provided OPTIONAL parameters can be omitted if not needed Parameters: Request Body: REQUIRED: - OutputFormat: OutputFormat parameter from application/json - Text: Text parameter from application/json - VoiceId: VoiceId parameter from application/json OPTIONAL: - Engine: Engine parameter from application/json - LanguageCode: LanguageCode parameter from application/json - SampleRate: SampleRate parameter from application/json - TextType: TextType parameter from application/json

Usage guide

## Authentication Create AWS IAM credentials with Amazon Transcribe and Polly permissions. Sign every request with AWS Signature Version 4 using an AWS SDK, CLI, or trusted signer. Never expose the secret access key. ## Speech to text Upload media to S3, then call the regional Transcribe endpoint with `X-Amz-Target: Transcribe.StartTranscriptionJob` and JSON containing `TranscriptionJobName`, `Media.MediaFileUri`, and one language selection. ## Text to speech Call the regional Polly `/v1/speech` endpoint with `OutputFormat`, `Text`, and `VoiceId`; the response is an audio stream. Official docs: https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html and https://docs.aws.amazon.com/polly/latest/APIReference/API_SynthesizeSpeech.html

How to use this spec

  1. Create a free VX Agents account (sandbox tools included).
  2. Open the marketplace and connect “Amazon Transcribe and Polly” to an agent.
  3. Expose it as an MCP server for Claude/ChatGPT, or chat with it directly.