All Providers

SpeechSDK supports 14 providers out of the box. Use provider/model strings to select a provider and model, or pass just the provider name to use its default model.

Browse the full list of models on the Models page, or jump into a provider page below.

Provider Table

Capability Matrix

Support is per-model — check each provider page for the per-model features. "STT fallback only" means timestamps: true works via a transcription round-trip (OpenAI Whisper by default); see the timestamps guide for details.

Usage

import { generateSpeech } from "@speech-sdk/core"

// provider/model string
await generateSpeech({
  model: "openai/gpt-4o-mini-tts",
  text: "Hello from SpeechSDK!",
  voice: "alloy",
})

// just the provider name uses the default model
await generateSpeech({
  model: "elevenlabs",
  text: "Hello from SpeechSDK!",
  voice: "EXAVITQu4vr4xnSDxMaL",
})

Provider Options

Each provider accepts provider-specific parameters via providerOptions. These are sent directly to the provider's API using the API's own field names.

const result = await generateSpeech({
  model: "openai/gpt-4o-mini-tts",
  text: "Hello!",
  voice: "alloy",
  providerOptions: {
    speed: 1.2,
    response_format: "opus",
  },
})

API Key Resolution

When using string models (e.g., 'openai/gpt-4o-mini-tts'), API keys are resolved from environment variables automatically (see the table above). You can override this with custom configuration.