Text to natural speech

Speech Generation

Generate speech with ElevenLabs, Gemini, OpenAI and Qwen voices through the OpenAI-compatible audio API.

Get startedRead the docs
POST /v1/audio/speech

Hello,welcometoLLMGateway!

3.1s
gemini-2.5-flash-preview-tts · voice Kore
01

Four providers

ElevenLabs, Gemini, OpenAI, Qwen.

02

Many voices

Pick the voice per request.

03

Streaming

Start playback before it finishes.

04

OpenAI format

Works with the OpenAI SDK.

Built for

  • Voice apps

    Read answers out loud

  • Narration

    Turn articles into audio

  • Accessibility

    Audio versions of any text

Make it talk
terminal
1curl https://api.llmgateway.io/v1/audio/speech \2  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "gemini-2.5-flash-preview-tts",6    "input": "Hello, welcome to LLM Gateway!",7    "voice": "Kore"8  }' \9  --output speech.wav
Read docs

More in models & modalities

All features

OCR

Documents and images to markdown

Embeddings

Vectors for search and RAG

Rerank

Sharper retrieval in one call

Start using Speech Generation today

One API key. Every model. Live in minutes.

Start buildingBrowse models