GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio, serving as OpenAI's premium transcription offering.
- Input
- audio text $2.5/M
- Output
- text $10/M
- Audio input
- $6/M
- Context
- 16K
- Knowledge cutoff
- 2024-06
Benchmarks
Vendor-published: Alibaba (Qwen) ByteDance Google OpenAI
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 | No |
| Streaming transcription | Yes |
| Timestamps | No |
Model
| Modalities | audio + text → text |
|---|
Use GPT-4o Transcribe 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",
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",
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" \
-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",
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")
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());About GPT-4o Transcribe
- The official page credits it with improvements to word error rate and better language recognition and accuracy compared with the original Whisper models.
- Requests carry a 16K-token context window with up to 2K output tokens, and the model is served across transcription and realtime endpoints.
- Uploads follow the shared limits of the transcription API: mp3, mp4, mpeg, mpga, m4a, wav, or webm, up to 25MB per file, with longer recordings split client-side.
- Unlike Whisper it accepts a prompt, which OpenAI describes as a way to improve transcription quality by giving the model additional context the same way you would prompt any other GPT-4o model, which is useful for names, jargon, and product spellings.
- Streaming transcription is supported, as are log probabilities for confidence-aware pipelines.
- Two limits shape integrations: output is available as JSON or plain text only, with no SRT, VTT, or verbose JSON, and word- or segment-level timestamp granularities are not offered on this model.
- Language coverage follows the transcription API's published list of more than seventy languages, which OpenAI gates on a word-error-rate threshold rather than claiming universal support, and the knowledge cutoff is June 2024.
- OpenAI frames it as the higher-accuracy choice where streaming is not the priority.
- On Synthorai it plugs into the OpenAI-compatible /v1/audio/transcriptions route unchanged.
FAQ
Is the GPT-4o Transcribe 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 against your real workload before adding a payment method.
What is GPT-4o Transcribe best at?
Premium transcription tier; better language recognition than original Whisper; served across transcription and realtime endpoints. See the About section for the full picture from the vendor's own release notes.
How much does GPT-4o Transcribe cost?
GPT-4o Transcribe costs $2.5 per million input tokens and $10 per million output tokens on Synthorai. That is the provider's list price, with no platform markup.
Which languages does GPT-4o Transcribe support?
GPT-4o Transcribe 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?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-4o-transcribe", 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.