version: "1.0.0" name: shellshock-stt description: Speech-to-text via ShellShock /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.

ShellShock — Speech-to-Text

Requires SHELLSHOCK_URL (and SHELLSHOCK_KEY if auth enabled). See https://raw.githubusercontent.com/theRizwan/ShellShock/refs/heads/main/skills/shellshock/SKILL.md for setup.

Discover

curl $SHELLSHOCK_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$SHELLSHOCK_URL/v1/models/info?id=openai/whisper-1"

model = STT model ID (e.g. openai/whisper-1, groq/whisper-large-v3, deepgram/nova-3, gemini/gemini-2.5-flash).

Endpoint

POST $SHELLSHOCK_URL/v1/audio/transcriptions (OpenAI Whisper compatible, multipart/form-data)

Examples

curl -X POST "$SHELLSHOCK_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $SHELLSHOCK_KEY" \
  -F "model=openai/whisper-1" \
  -F "file=@audio.mp3" \
  -F "language=vi"

JS (Node):

import { createReadStream } from "node:fs";
const form = new FormData();
form.append("model", "groq/whisper-large-v3-turbo");
form.append("file", new Blob([await (await import("node:fs/promises")).readFile("audio.mp3")]), "audio.mp3");
const r = await fetch(`${process.env.SHELLSHOCK_URL}/v1/audio/transcriptions`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.SHELLSHOCK_KEY}` },
  body: form,
});
const { text } = await r.json();
console.log(text);

Response shape

Default (response_format=json):

{ "text": "Xin chào, đây là bản ghi âm." }

verbose_json adds language, duration, segments[] with timestamps. srt / vtt return subtitle text.

Provider quirks