Built for voice agents that can't wait 600ms
Sign up freeSign in

OpenAI: GPT Live Transcribe

openai/gpt-live-transcribe
active stt 1 provider
Playground

OpenAI's recommended default for live speech-to-text, with tunable latency (delay levels) and context hints, streaming only.

AuthorOpenAI
Languagesmultilingual
Statusactive

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer hourLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
OpenAI 2 params
openai
$1.02
—
Streaming

Supported languages

No reviewed language list for this model yet.

Features

Speech to text

Transcribes spoken audio to text.

speech_to_text
Streaming

Real-time transcription over the WebSocket Realtime API.

streaming
Multilingual transcription

Multilingual transcription with automatic language detection.

multilingual_transcription
Tunable latency

The delay parameter trades latency against accuracy: minimal, low, medium, high, or xhigh.

tunable_latency
Context hints

Steers transcription with prompt (free-form context about the recording), keywords (literal terms that may appear in the audio, e.g. product names), and languages (expected ISO 639-1 codes).

context_hints

Code

Client
Mode
Language

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "openai/gpt-live-transcribe",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "openai"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.