GPT-4o Transcribe Diarize is an automatic speech recognition model that identifies who is speaking when: it associates audio segments with different speakers in a conversation, so transcripts capture who said what, not just what was said.
- Input
- audio text $2.5/M
- Output
- text $2.5/M
- Audio input
- $6.25/M
- Context
- 16K
- Knowledge cutoff
- 2024-06
Price in context
Where the price sits among 3 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Max output (vendor spec) | 2,000 |
|---|---|
| Knowledge cutoff | 2024-06 |
Audio
| Languages | 57 languages listed for the transcriptions endpoint (one shared list for all transcription models); ISO 639-1 / 639-3 codes accepted for GPT-4o-based models |
|---|---|
| Audio limits |
|
| Speaker diarization | Yes |
| Streaming transcription | Yes |
| Timestamps | Yes |
Model
| Modalities | audio + text → text |
|---|
Only OpenAI transcription model with built-in speaker diarization.
Use GPT-4o Transcribe Diarize in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/audio/transcriptions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.audio.transcriptions.create(
model="gpt-4o-transcribe-diarize",
file=open("meeting.mp3", "rb"),
language="en",
)
print(resp.text)import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.audio.transcriptions.create({
model: "gpt-4o-transcribe-diarize",
file: fs.createReadStream("meeting.mp3"),
});
console.log(resp.text);curl https://synthorai.io/v1/audio/transcriptions \
-H "Authorization: Bearer sk-syn-..." \
-F model="gpt-4o-transcribe-diarize" \
-F file=@meeting.mp3package main
import (
"context"
"fmt"
"os"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
f, _ := os.Open("meeting.mp3")
resp, _ := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
Model: "gpt-4o-transcribe-diarize",
File: f,
})
fmt.Println(resp.Text)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.audio.transcriptions.*;
import java.nio.file.Paths;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
Transcription resp = client.audio().transcriptions().create(
TranscriptionCreateParams.builder()
.model("gpt-4o-transcribe-diarize")
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());About GPT-4o Transcribe Diarize
- It shares the GPT-4o transcription family's 16K-token context window and 2K max output tokens and is purpose-built for the transcription endpoint rather than general chat.
- OpenAI states plainly that the model is available only through the Transcription API and not in the Realtime API.
- It is the only OpenAI model that returns the diarized JSON response format, which carries speaker labels alongside segment timestamps; plain JSON and text are also available, but SRT, VTT, and verbose JSON are not.
- Two behaviours are specific to this model.
- A chunking strategy is required for audio longer than 30 seconds, either automatic or a voice-activity configuration you supply, and prompting is not available at all, so the context tricks that work on its siblings do not apply here.
- Speakers can optionally be named in advance by supplying up to four short reference clips of a few seconds each.
- Streaming works, though speaker assignment finalizes per segment rather than word by word.
- Meeting notes, call analytics, and interview tooling are its natural fit.
- Synthorai exposes it through the same OpenAI-compatible transcription API as its siblings.
FAQ
Is the GPT-4o Transcribe Diarize API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try GPT-4o Transcribe Diarize against your real workload before adding a payment method.
What is GPT-4o Transcribe Diarize best at?
Built-in speaker diarization; transcripts capture who said what; fits meeting notes and call analytics. See the About section for the full picture from the vendor's own release notes.
How much does GPT-4o Transcribe Diarize cost?
GPT-4o Transcribe Diarize costs $2.5 per million input tokens and $2.5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup.
Which languages does GPT-4o Transcribe Diarize support?
GPT-4o Transcribe Diarize supports 57 languages listed for the transcriptions endpoint (one shared list for all transcription models); ISO 639-1 / 639-3 codes accepted for GPT-4o-based models. On Synthorai you call it through POST /v1/audio/transcriptions, the OpenAI transcription API shape.
How do I get access to GPT-4o Transcribe Diarize?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-4o-transcribe-diarize", and you're done. One API key covers every model on the gateway.
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.