Live market

gpt-4o-transcribe

OpenAI: GPT-4o Transcribe

Of list price: 100%
Output / 1M: 10.00 USDT
Sellers online: 50
Calls / min: 0

Calling this model

POST /audio/transcriptions — the same request OpenAI's SDKs already send. Point the base URL at asale and change nothing else.

billed per token

INPUT

The recording, base64-encoded.

Container the recording is in.

Spoken language; detected when omitted.

verbose_json adds language, duration and timestamps.

Higher is more varied; 0 is deterministic.

Minimum charge per request: 0.000013 USDT

Output

Run it to see the answer here.

Or call it from your own code

curl https://gw.asale.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $ASALE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-transcribe",
    "input_audio": {
      "data": "<base64>",
      "format": "wav"
    },
    "response_format": "json"
  }'

import os, requests

r = requests.post(
    "https://gw.asale.ai/v1/audio/transcriptions",
    headers={"Authorization": f"Bearer {os.environ['ASALE_API_KEY']}"},
    json={
      "model": "gpt-4o-transcribe",
      "input_audio": {
        "data": "<base64>",
        "format": "wav"
      },
      "response_format": "json"
    },
)
r.raise_for_status()
print(r.json())

const r = await fetch("https://gw.asale.ai/v1/audio/transcriptions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ASALE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "gpt-4o-transcribe",
    "input_audio": {
      "data": "<base64>",
      "format": "wav"
    },
    "response_format": "json"
  }),
});
if (!r.ok) throw new Error(await r.text());
console.log(await r.json());

Request fields

Field	Type	Accepts	Meaning
modelrequired	string	—	Which model serves the request.
input_audio.datarequired	audio	—	The recording, base64-encoded.
input_audio.formatrequired	enum	wav · mp3 · flac · m4a · ogg · webm · aac	Container the recording is in.
language	string	—	Spoken language; detected when omitted.
response_format	enum	json · verbose_json	verbose_json adds language, duration and timestamps.
temperature	number	0 … 1	Higher is more varied; 0 is deterministic.

Response

{
  "text": "Hello from the asale media market.",
  "usage": {
    "seconds": 3,
    "input_tokens": 27,
    "output_tokens": 9,
    "cost": 0.0003
  }
}

Token type	List / 1M	Market / 1M	Of list price
Input	2.50	2.50	100%
Output	10.00	10.00	100%
Cache read	2.50	2.50	100%
Cache write	2.50	2.50	100%

Channel quality

What has been measured about the supply behind this price. Readings, not promises — and aggregate, because which seller failed is nobody's business but theirs and ours.

Online lanes: 50
Verified lanes: 1/1; Proved they serve this model
First byte (p50): —
Success rate: —; No turns settled in the window
Sellable capacity: 100.0M; Tokens offered right now

Latency and verification are measured over the last day; the success rate comes from settled traffic. See the status page

Price trend

Currently selling at 100% of the vendor's list price. More sellers online push it down; more buyers push it back up to list.

Of list price: 100%
Sellers online: 50
Calls / min: 0

Market depth

Price / 1MSellers

10.00