Azure-Samples/cognitive-services-speech-sdk

Sample code for the Microsoft Cognitive Services Speech SDK

What it solves

This repository provides practical code examples to help developers integrate speech-enabled features into their applications using the Microsoft Cognitive Services Speech SDK. It bridges the gap between documentation and implementation by providing ready-to-run samples for various platforms and languages.

How it works

The project hosts a collection of quickstarts and complex scenarios that utilize the Azure Speech SDK. These samples demonstrate how to interact with Azure's speech services via subscription keys, covering three primary modalities:

  • Speech Recognition: Converting spoken audio from a microphone or file into text.
  • Speech Translation: Translating spoken audio into text in another language.
  • Speech Synthesis: Converting text into spoken audio (text-to-speech) played through a speaker.

Who it’s for

Developers building cross-platform applications (Windows, Linux, macOS, Android, iOS, and Web) who need to add voice interfaces, transcription services, or translation capabilities using C++, C#, Java, JavaScript/Node.js, Python, Objective-C, or Swift.

Highlights

  • Multi-language support: Examples provided for a wide array of programming languages.
  • Cross-platform coverage: Samples for desktop, mobile, and web environments.
  • Coded examples for core features: Dedicated quickstarts for one-shot recognition, translation, and synthesis.
  • Advanced scenarios: Includes samples for batch transcription, batch synthesis, and audio device enumeration.

Related

  • Project
    Azure-Samples/Cognitive-Speech-TTS

    A Microsoft‑maintained repo of SDK and REST code samples showing how to use Azure Cognitive Services Speech (Text‑to‑Speech), with links to customer stories, blog posts, and research. Ideal for developers who need ready‑to‑run examples for realistic, multilingual synthetic voices, custom neural voices, and related Azure Speech features.

  • Project
    Migushthe2nd/MsEdgeTTS

    MsEdgeTTS is a Node.js library that streams neural‑quality text‑to‑speech audio using Microsoft Edge’s free Read Aloud API, with support for voice selection, output format choice, rate/pitch/volume tweaks, and optional word‑/sentence‑boundary metadata.

  • Project
    microsoft/cognitive-services-speech-sdk-js

    A JavaScript SDK for integrating Microsoft Cognitive Services speech capabilities, enabling speech-to-text and text-to-speech functionality in browsers and Node.js.

  • Project
    microsoft/skills

    Microsoft / skills is a genuine open‑source toolbox that equips AI coding agents (e.g., GitHub Copilot) with ready‑made, Azure‑specific “skills” – code snippets, templates, and MCP server scaffolding – so the agents can generate correct Azure SDK calls, manage Foundry resources, and follow governance patterns. Install via `npx skills add microsoft/skills`, pick only the needed skills (≈175 across Python, .NET, TypeScript, Java, Rust), and use the provided `AGENTS.md` and MCP configs to build custom agents for backend, frontend, infrastructure, or planning tasks.

  • Project
    aliyun/alibabacloud-bailian-speech-demo

    A collection of development examples for Alibaba Cloud Bailian, enabling developers to implement speech recognition, synthesis, and real-time voice dialogue using Qwen-Audio and other models.