​
Supported Providers

  • OpenAI
  • Azure OpenAI
The speech API takes as input the text you want to convert to speech and generates high-quality audio using advanced text-to-speech models. All models support the same set of text inputs with a maximum length of 4,096 characters. On output, you can choose from various audio formats (mp3, opus, aac, flac, wav, pcm) and different voice options (alloy, echo, fable, onyx, nova, shimmer).

​
Code Snippet

from pathlib import Path
from openai import OpenAI

BASE_URL = "https://{controlPlaneUrl}/api/llm"
API_KEY = "your-truefoundry-api-key"

client = OpenAI(
    api_key=API_KEY,
    base_url=BASE_URL,
)

speech_file_path = Path(__file__).parent / "generated-audio.mp3"

with client.audio.speech.with_streaming_response.create(
  model="openai-main/gpt-4o-mini-tts",
  voice="alloy",
  input="hello how are you?"
) as response:
  response.stream_to_file(speech_file_path)
The API generates audio files in the specified format (defaults to MP3) with the selected voice characteristics.