Transcription · Transcription
Groq Whisper API
Groq-hosted Whisper. Faster inference.
- Price
- From $0.03 per run
- Typical time
- ~5 s
- Model id
groq_whisper
Groq Whisper runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/transcription/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "groq_whisper",
"audio_url": "https://example.com/audio.mp3"
}'Groq Whisper pricing
From $0.03 per run. Prices are in US dollars and are the provider's own, with no markup. Groq Whisper has 2 routes: "model": "groq_whisper" picks one automatically, or pass a route key as "model" to pin it. For the exact price of a request, send the same body to POST https://api.varg.ai/v2/estimate.
- groq $0.06
groq:whisper_large_v3Transcription
- Fixed price
- $0.06
- Typical time
- ~5 s
- groq $0.03
groq:whisper_large_v3_turboTranscription
- Fixed price
- $0.03
- Typical time
- ~5 s
Groq Whisper inputs
The JSON body of the request. Media inputs are URLs: upload a local file with POST /v2/files and pass the URL it returns. Full JSON Schema, no key needed: api.varg.ai/v2/tools/transcription?model=groq_whisper
| Field | What it does |
|---|---|
model string required | groq_whisper picks a route automatically. To pin one, pass a route key from Pricing above. |
prompt string | — |
audio_url string (URL) required | — |
language string | Allowed e.g. en | ru | es | de | fr | it | pt | ja | ko | zh | hi | ar |
Provider options
Optional, under provider_options.<provider>. Only the options of the provider that runs the job apply; pin a route to choose it.
provider_options.groq
| Field | What it does |
|---|---|
language string | Allowed e.g. en | ru | es | de | fr | it | pt | ja | ko | zh | hi | ar |
audio_url string (URL) | — |
Call the Groq Whisper API
POST https://api.varg.ai/v2/tools/transcription/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away.
1. Send the request
curl -X POST https://api.varg.ai/v2/tools/transcription/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "groq_whisper",
"audio_url": "https://example.com/audio.mp3"
}'JavaScript
const headers = {
Authorization: `Bearer ${process.env.VARG_API_KEY}`,
'Content-Type': 'application/json',
}
const res = await fetch('https://api.varg.ai/v2/tools/transcription/call', {
method: 'POST',
headers,
body: JSON.stringify({
"model": "groq_whisper",
"audio_url": "https://example.com/audio.mp3"
}),
})
const job = await res.json() // { id: "job_…", status: "queued" }Python
import os
import requests
headers = {"Authorization": f"Bearer {os.environ['VARG_API_KEY']}"}
job = requests.post(
"https://api.varg.ai/v2/tools/transcription/call",
headers=headers,
json={
"model": "groq_whisper",
"audio_url": "https://example.com/audio.mp3"
},
).json() # {"id": "job_…", "status": "queued"}2. Get the result
Poll the job until its status is completed, failed or cancelled; Groq Whisper typically takes about 5 s. The result is at output.outputs[0].url.
curl https://api.varg.ai/v2/jobs/$JOB_ID \
-H "Authorization: Bearer $VARG_API_KEY"
# Poll until "status" is completed, failed or cancelled.
# The result is in output.outputs[0].urlJavaScript
let current = job
while (!['completed', 'failed', 'cancelled'].includes(current.status)) {
await new Promise((resolve) => setTimeout(resolve, 3000))
current = await (await fetch(`https://api.varg.ai/v2/jobs/${current.id}`, { headers })).json()
}
console.log(current.output?.outputs?.[0]?.url)Python
import time
while job["status"] not in ("completed", "failed", "cancelled"):
time.sleep(3)
job = requests.get(f"https://api.varg.ai/v2/jobs/{job['id']}", headers=headers).json()
print(job["output"]["outputs"][0]["url"])Or take a webhook instead of polling
Add options.webhook_url and varg POSTs the finished job to it.
{
"model": "groq_whisper",
"audio_url": "https://example.com/audio.mp3",
"options": {
"webhook_url": "https://your-app.com/varg-webhook"
}
}From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs Groq Whisper with call_tool. Sign in with varg, no API key to paste. How to connect it
{
"tool": "transcription",
"input": {
"model": "groq_whisper",
"audio_url": "https://example.com/audio.mp3"
},
"wait": true
}Groq Whisper API: questions
- How much does Groq Whisper cost on varg?
- Groq Whisper costs from $0.03 per run on varg. varg charges the provider's price with no markup, from one credit balance. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- How do I call the Groq Whisper API?
- Send POST https://api.varg.ai/v2/tools/transcription/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model": "groq_whisper". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use Groq Whisper from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs Groq Whisper with call_tool, passing tool "transcription" and "model": "groq_whisper".
- How long does a Groq Whisper request take?
- Typically about 5 s on the fastest route, by the catalog's estimate. The API answers at once with a job id, so nothing waits on an open connection while it runs.
For AI agents: this page as Markdown is varg.ai/models/groq_whisper.md, and every model is listed in varg.ai/models/llms.txt.