5 models · transcription
Whisper API
Whisper is a family of AI transcription models made by OpenAI. varg runs 5 of them on one API key: Groq Whisper Turbo, Groq Whisper, Groq Whisper Large v3 and 2 more. Between them they cover transcription; they return JSON.
- Price
- From $0.03 per run Groq Whisper Turbo
- Made by
- OpenAI
- Flagship id
groq_whisper_large_v3_turbo
Every Whisper model 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_large_v3_turbo",
"audio_url": "https://example.com/audio.mp3"
}'Whisper models and prices
Whisper on varg starts from $0.03 per run (Groq Whisper Turbo). Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
Groq Whisper Turbogroq_ | Groq-accelerated Whisper. | Transcription | From $0.03 per run | ~5 s |
Groq Whispergroq_ | Groq-hosted Whisper. Faster inference. | Transcription | From $0.03 per run | ~5 s |
Groq Whisper Large v3groq_ | Groq-hosted Whisper Large v3. Fast inference with high accuracy. | Transcription | From $0.06 per run | ~5 s |
Whisperwhisper | OpenAI Whisper via fal. Accurate speech-to-text. | Transcription | From $0.05 per run | ~30 s |
Whisper Large v3whisper_ | OpenAI Whisper Large v3 via fal. Higher accuracy for complex audio. | Transcription | From $0.05 per run | ~30 s |
Call the Whisper API
The call below runs Groq Whisper Turbo. For another Whisper model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/transcription/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
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_large_v3_turbo",
"audio_url": "https://example.com/audio.mp3"
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs Groq Whisper Turbo with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "transcription",
"input": {
"model": "groq_whisper_large_v3_turbo",
"audio_url": "https://example.com/audio.mp3"
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool transcription '{"model":"groq_whisper_large_v3_turbo","audio_url":"https://example.com/audio.mp3"}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
How to use Whisper
Step-by-step pages on varg how to.
Whisper API: questions
- How much does the Whisper API cost on varg?
- The lowest price the catalog states in the Whisper family is from $0.03 per run, on Groq Whisper Turbo and Groq Whisper. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which Whisper models are on varg?
- 5: Groq Whisper Turbo (from $0.03 per run), Groq Whisper (from $0.03 per run), Groq Whisper Large v3 (from $0.06 per run), Whisper (from $0.05 per run) and Whisper Large v3 (from $0.05 per run). Each has its own page with the parameters and a call to copy.
- How long do Whisper requests take?
- Typically from about 5 s (Groq Whisper Turbo) to about 30 s (Whisper), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the 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", for example "model": "groq_whisper_large_v3_turbo". 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 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 a model with call_tool, passing tool "transcription" and the model id, for example "model": "groq_whisper_large_v3_turbo".
For AI agents: each model above has its full spec as Markdown at varg.ai/models/groq_whisper_large_v3_turbo.md (swap the id), and every model is listed in varg.ai/models/llms.txt.