GPT-4o Mini Transcribe is a speech-to-text model powered by GPT-4o mini, offering improvements to word error rate and better language recognition and accuracy compared with the original Whisper models.
- Input
- audio text $1.25/M
- Output
- text $5/M
- Audio input
- $3/M
- Context
- 16K
- Knowledge cutoff
- 2024-06
Benchmarks
GPT-4o Mini Transcribe: 33 published, but no benchmark it shares with enough other models to compare.
Vendor-published: 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 |
|---|
Cost-efficient tier of GPT-4o transcription.
Use GPT-4o Mini 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-mini-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-mini-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-mini-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-mini-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-mini-transcribe")
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());About GPT-4o Mini Transcribe
- It is the cost-effective option in OpenAI's transcription lineup, priced at half of GPT-4o Transcribe's audio-input rate, with a 16K-token context window and up to 2K output tokens per request.
- It shares the family's operational envelope: mp3, mp4, mpeg, mpga, m4a, wav, or webm files up to 25MB, streaming transcription, prompt-based context injection for names and domain vocabulary, and log probabilities on request, with output limited to JSON or plain text and no timestamp granularities.
- Two changes are worth pinning a snapshot for.
- OpenAI moved the undated alias onto a December 2025 snapshot, so integrations that never pinned a version silently changed models, and the original March 2025 snapshot has since been scheduled for retirement.
- Batch API support was added in early 2026, which makes large offline backlogs cheaper to clear.
- Like its larger sibling it is served on both the transcription endpoint and realtime transcription sessions, covers the transcription API's published list of more than seventy languages, and carries a June 2024 knowledge cutoff.
- It suits high-volume transcription pipelines where accuracy still matters but per-token audio cost decides the architecture, and where a diarized transcript or subtitle timings are not required.
- Synthorai handles it through the OpenAI-compatible audio transcription endpoint.
FAQ
Is the GPT-4o Mini 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 Mini Transcribe against your real workload before adding a payment method.
What is GPT-4o Mini Transcribe best at?
Improved word error rate over original Whisper; half the premium tier's audio-input rate; 16K context with up to 2K output. See the About section for the full picture from the vendor's own release notes.
How much does GPT-4o Mini Transcribe cost?
GPT-4o Mini Transcribe costs $1.25 per million input tokens and $5 per million output tokens on Synthorai. That is the provider's list price, with no platform markup.
Which languages does GPT-4o Mini Transcribe support?
GPT-4o Mini 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 Mini Transcribe?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-4o-mini-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.