Transcribe with word and segment timestamps (Whisper)

Liveby OpenAI

Transcribe public audio with whisper-1 and return both word and segment timestamps in seconds, plus the complete raw verbose_json response.

At most 25 MB and 60 seconds; max_minutes defaults to 1. Fully decoded sample frames enforce the limit before the paid call; only canonical mono PCM WAV is uploaded. Duration-based price; measured-duration cost is explicitly estimated when OpenAI omits usage.

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Transcribe this meeting recording and list the action items.

Turn this voice note into text.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Speech to text API by OpenAI, callable through Superpowers. It costs $0.0069 per minute, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "openai.whisper-timestamps", or over MCP with run_tool. 5 other providers in this category take the same input and can be compared side by side.

Tool id
Price per call: $0.0069 / minute

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"openai.whisper-timestamps","input":{"audio_url":""},"idempotency_key":"example-request-1"}'

Input

3 fields · 1 required

{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "audio_url"
  ],
  "properties": {
    "audio_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2000,
      "description": "Public HTTP(S) audio file, at most 25 MB. Redirects must also be public."
    },
    "language": {
      "type": "string",
      "pattern": "^[a-z]{2}$",
      "description": "Optional ISO-639-1 language, e.g. en or pt; omit for automatic detection."
    },
    "max_minutes": {
      "type": "number",
      "exclusiveMinimum": 0,
      "maximum": 1,
      "default": 1,
      "description": "Reject longer audio BEFORE calling OpenAI. Does not truncate the file."
    }
  }
}