Skip to main content
Audio transcription turns speech (audio files) into text. The gateway supports two ways to call it:
ApproachUse forBase path
Unified API (OpenAI-compatible)OpenAI, Azure OpenAI, Groqhttps://{controlPlaneUrl}/api/llm
Provider proxy (native SDK)Deepgram, Cartesia, ElevenLabshttps://{controlPlaneUrl}/stt/{providerAccountName}
Before you start: Replace {controlPlaneUrl} with your gateway URL and your-tfy-api-key with your TrueFoundry API key. For the provider proxy, replace {providerAccountName} with the display name of your provider account on TrueFoundry.
Model names: For audio (STT/TTS), the model ID in code must match the display name of the model on your TrueFoundry provider account.
Which SDK to use: For OpenAI, Azure OpenAI, and Groq, use the OpenAI SDK (same API). For Deepgram, Cartesia, and ElevenLabs, use each provider’s native SDK with the gateway URL above.

​
Code snippets

from openai import OpenAI

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

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

with open("/path/to/audio.mp3", "rb") as audio_file:
    response = client.audio.transcriptions.create(
        model="openai-main/whisper-1",  # truefoundry model name
        file=audio_file,
    )

print(response)

​
Response

The shape of the response depends on the provider. Use print(response) to inspect it, or refer to each provider’s SDK docs for the exact structure.