Skip to main content
skill CX Codex

9routerx-stt — Claude Code skill: what it does, how to install

9routerx-stt — a skill for Claude Code and Codex that routes audio transcription requests through 9RouterX. Transcribes voice recordings and generates subtitle files across multiple model backends.

MIT ★ 259 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add yanstd888/9routerx --skill 9routerx-stt -a claude-code
Open on GitHub

What 9routerx-stt does

This skill routes speech recognition requests through the OpenAI Whisper compatible POST /v1/audio/transcriptions endpoint. The agent uploads audio files in mp3, wav, m4a, webm, ogg, or flac formats, selects a target model, and can optionally specify an ISO-639-1 language code, prompt hint, or temperature. The output returns plain text, standard JSON, verbose JSON with segment timestamps, or subtitle files in srt and vtt formats.

The backend server normalizes requests for specific providers automatically. It maps calls to inline audio payloads for Gemini, handles asynchronous upload polling for AssemblyAI, and sets provider-specific auth headers. For ElevenLabs, passing both diarize and num_speakers invalidates the request upstream, so the server prioritizes diarization and drops speaker counts.

Running queries requires the 9ROUTERX_URL environment variable, plus 9ROUTERX_KEY whenever authentication is enforced. Available models can be discovered dynamically via the /v1/models/stt endpoint.

What it helps with

  • transcribe recorded interviews and podcasts from audio files
  • build srt or vtt subtitle tracks directly from audio tracks
  • extract timestamps and segments with verbose JSON responses
  • switch between speech backends like Groq, OpenAI, and Deepgram

Example prompts for the agent

  • Transcribe audio.mp3 using the groq/whisper-large-v3-turbo model
  • Generate srt subtitles from meeting.wav with language set to en
  • Convert podcast.m4a to text using deepgram/nova-3 with timestamps

How to install 9routerx-stt

1Skills CLI (Vercel)

npx skills add yanstd888/9routerx --skill 9routerx-stt -a claude-code

2Manually: put the files in place

~/.claude/skills/9routerx-stt/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/9routerx-stt/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about 9routerx-stt

How to install 9routerx-stt in Claude Code?

Run npx skills add yanstd888/9routerx --skill 9routerx-stt -a claude-code. The definition will be placed in ~/.claude/skills/9routerx-stt/SKILL.md.

What does 9routerx-stt do?

It bridges coding agents with the 9RouterX gateway to convert voice recordings into text, detailed timestamp segments, or subtitles.

What is required to run 9routerx-stt?

You need an accessible 9RouterX instance defined in 9ROUTERX_URL, along with 9ROUTERX_KEY if the proxy requires bearer authentication.

Source text

SKILL.md · MIT
---
name: 9routerx-stt
description: Speech-to-text via 9RouterX /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.
---

# 9RouterX — Speech-to-Text

Requires `9ROUTERX_URL` (and `9ROUTERX_KEY` if auth enabled). See https://raw.githubusercontent.com/yanstd888/9routerx/refs/heads/main/skills/9routerx/SKILL.md for setup.

## Discover

```bash
curl $9ROUTERX_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$9ROUTERX_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 $9ROUTERX_URL/v1/audio/transcriptions` (OpenAI Whisper compatible, `multipart/form-data`)

| Field | Required | Notes |
|---|---|---|
| `model` | yes | from `/v1/models/stt` |
| `file` | yes | audio file (mp3, wav, m4a, webm, ogg, flac) |
| `language` | no | ISO-639-1 (e.g. `en`, `vi`) |
| `prompt` | no | hint text to guide transcription |
| `response_format` | no | `json` (default) / `text` / `verbose_json` / `srt` / `vtt` |
| `temperature` | no | 0–1 |

## Examples

```bash
curl -X POST "$9ROUTERX_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $9ROUTERX_KEY" \
  -F "model=openai/whisper-1" \
  -F "[email protected]" \
  -F "language=vi"
```

JS (Node):

```js
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.9ROUTERX_URL}/v1/audio/transcriptions`, {
  method: "POST",
  headers: { "Authorization": `Bearer ${process.env.9ROUTERX_KEY}` },
  body: form,
});
const { text } = await r.json();
console.log(text);
```

## Response shape

Default (`response_format=json`):
```json
{ "text": "Xin chào, đây là bản ghi âm." }
```

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

## Provider quirks

| Provider | `model` format | Notes |
|---|---|---|
| `openai` | `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` | Native OpenAI shape |
| `groq` | `whisper-large-v3`, `whisper-large-v3-turbo`, `distil-whisper-large-v3-en` | Fastest; OpenAI shape |
| `gemini` | `gemini-2.5-flash`, `gemini-2.5-pro`, `gemini-2.5-flash-lite` | Server converts to `generateContent` with audio inline |
| `deepgram` | `nova-3`, `nova-2`, `whisper-large` | Token auth; server adapts response |
| `assemblyai` | `universal-3-pro`, `universal-2` | Async upload+poll handled server-side |
| `nvidia` | `nvidia/parakeet-ctc-1.1b-asr` | NIM endpoint |
| `huggingface` | `openai/whisper-large-v3`, `openai/whisper-small` | HF Inference API |
| `elevenlabs` | `scribe_v1`, `scribe_v2` | Whisper-compatible shape; `xi-api-key` auth, not Bearer. Extra params: `timestamps_granularity` (`word`/`character`/`none`), `tag_audio_events`, and speaker labelling via **either** `diarize=true` **or** `num_speakers` (1–32) — sending both makes the request invalid, so `diarize` wins and `num_speakers` is dropped. Blank `language` is omitted upstream for auto-detect. `srt`/`vtt` and `verbose_json` segments are served from Scribe's own `additional_formats` render, so `segments[]` is omitted when the upstream render is unavailable rather than synthesized. Does not accept `temperature` or `prompt` — those are not forwarded. |

© yanstd888 · MIT · yanstd888/9routerx

Similar skills

All skills for AI and ML →

From the same set9

9routerx-embeddings The 9routerx-embeddings Claude Code skill creates text embeddings through the 9RouterX API. The agent uses it for RAG, semantic search, and text similarity tasks. CX Codex +1 ★ 259repo stars 9routerx-chat The 9routerx-chat Claude Code skill sends language-model requests through 9RouterX. It activates for code generation, text summaries, and other prompts to a model. CX Codex +1 ★ 259repo stars 9routerx Claude Code skill connects your agent to the 9RouterX gateway. It routes OpenAI-compatible REST calls for chat, speech, embeddings, and web fetch to multiple AI models. CX Codex +1 ★ 259repo stars 9routerx-tts The 9routerx-tts Claude Code skill turns text into speech through the 9RouterX API. It runs for voiceovers, generated audio, or reading text aloud. CX Codex +1 ★ 259repo stars 9routerx-image The 9routerx-image Claude Code skill creates images through the 9RouterX API. It activates when a request asks for a picture or text-to-image generation. CX Codex +1 ★ 259repo stars 9routerx-web-fetch The 9routerx-web-fetch Claude Code skill retrieves webpage content as Markdown, plain text, or HTML. The agent uses it to read an article or extract material from a URL. CX Codex +1 ★ 259repo stars 9routerx-video The 9routerx-video Claude Code skill creates videos through xAI Grok Imagine. It runs when asked to generate a clip from text or an image. CX Codex +1 ★ 259repo stars 9routerx-web-search The 9routerx-web-search Claude Code skill searches the web and public X posts through 9RouterX. It runs when an agent is asked to find articles, information, or posts on X. CX Codex +1 ★ 259repo stars

Project sponsors

Companies that keep this analytics open