OpenAI: GPT-4o Transcribe Diarize
openai/gpt-4o-transcribe-diarize
active
stt
1 provider
OpenAI speaker-aware transcription model with diarization (labels who spoke when), built on GPT-4o Transcribe.
AuthorOpenAI
Languages1 languages
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 1M tokensLatencyiFor TTS, latency is measured as time to first byte of audio. For STT, latency is measured as time to first token.ModesUptime
OpenAI
4 params
openai
$2.5
—
Synchronous
Supported languages
1 languages
English
en
Features
Speech to text
Transcribes spoken audio to text.
speech_to_text
Synchronous
Transcribes a fully-submitted audio file in a single synchronous request via POST /v1/audio/transcriptions.
synchronous
Multilingual transcription
Supports 99 languages.
multilingual_transcription
Speaker diarization
Labels who spoke when (diarized_json); up to 4 known speakers with reference samples.
speaker_diarization
Code
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-4o-transcribe-diarize",
languageCode: "en"
}, {
queryParams: {
provider: {
"only": [
"openai"
]
}
}
});
// Send audio frames to connection, then handle transcript events.