Providers

SpeechSDK supports 12 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 providers and models on the Models page.

Provider Table

Provider	Prefix	Default Model	Env Var
OpenAI	`openai`	`gpt-4o-mini-tts`	`OPENAI_API_KEY`
ElevenLabs	`elevenlabs`	`eleven_multilingual_v2`	`ELEVENLABS_API_KEY`
Deepgram	`deepgram`	`aura-2`	`DEEPGRAM_API_KEY`
Cartesia	`cartesia`	`sonic-3`	`CARTESIA_API_KEY`
Hume	`hume`	`octave-2`	`HUME_API_KEY`
Google	`google`	`gemini-2.5-flash-preview-tts`	`GOOGLE_API_KEY`
Fish Audio	`fish-audio`	`s2-pro`	`FISH_AUDIO_API_KEY`
Unreal Speech	`unreal-speech`	`default`	`UNREAL_SPEECH_API_KEY`
Murf	`murf`	`GEN2`	`MURF_API_KEY`
Resemble	`resemble`	`default`	`RESEMBLE_API_KEY`
fal	`fal-ai`	(user-specified)	`FAL_API_KEY`
Mistral	`mistral`	`voxtral-mini-tts-2603`	`MISTRAL_API_KEY`

Usage Examples

OpenAI

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

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

OpenAI models: gpt-4o-mini-tts, tts-1, tts-1-hd

ElevenLabs

const result = await generateSpeech({
  model: "elevenlabs/eleven_multilingual_v2",
  text: "Hello from SpeechSDK!",
  voice: "EXAVITQu4vr4xnSDxMaL",
})

ElevenLabs models: eleven_v3, eleven_multilingual_v2, eleven_flash_v2_5, eleven_flash_v2

Deepgram

const result = await generateSpeech({
  model: "deepgram/aura-2",
  text: "Hello from SpeechSDK!",
  voice: "thalia-en",
})

Cartesia

const result = await generateSpeech({
  model: "cartesia/sonic-3",
  text: "Hello from SpeechSDK!",
  voice: "a0e99841-438c-4a64-b679-ae501e7d6091",
})

Cartesia models: sonic-3, sonic-2

Google (Gemini TTS)

const result = await generateSpeech({
  model: "google/gemini-2.5-flash-preview-tts",
  text: "Hello from SpeechSDK!",
  voice: "Kore",
})

Hume

const result = await generateSpeech({
  model: "hume/octave-2",
  text: "Hello from SpeechSDK!",
  voice: "Dacher",
})

Mistral

const result = await generateSpeech({
  model: "mistral/voxtral-mini-tts-2603",
  text: "Hello from SpeechSDK!",
  voice: { audio: "base64-encoded-audio..." },
})

Mistral uses voice cloning by default — pass a voice object with reference audio.

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/tts-1'), API keys are resolved from environment variables automatically (see the table above). You can override this with custom configuration.

Providers

On this page