Keirouter Stt
mydisha/keirouter
Speech-to-text via KeiRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI models.
Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others.
Install 9Router Speech-to-Text
$ npx skills add decolua/9router --skill 9router-stt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install decolua/9router 9router-stt --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/9router-stt .claude/skills/9router-stt && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "9router-stt" agent skill from https://github.com/decolua/9router/tree/master/skills/9router-stt into .claude/skills/9router-stt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "9router-stt", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/decolua/9router/tree/master/skills/9router-sttType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add decolua/9router --skill 9router-stt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install decolua/9router 9router-stt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/9router-stt .agents/skills/9router-stt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "9router-stt" agent skill from https://github.com/decolua/9router/tree/master/skills/9router-stt into .agents/skills/9router-stt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "9router-stt", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add decolua/9router --skill 9router-stt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install decolua/9router 9router-stt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/9router-stt .cursor/skills/9router-stt && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "9router-stt" agent skill from https://github.com/decolua/9router/tree/master/skills/9router-stt into .cursor/skills/9router-stt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "9router-stt", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/decolua/9router.git --path skills/9router-stt--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add decolua/9router --skill 9router-stt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install decolua/9router 9router-stt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/9router-stt .gemini/skills/9router-stt && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "9router-stt" agent skill from https://github.com/decolua/9router/tree/master/skills/9router-stt into .gemini/skills/9router-stt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "9router-stt", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install decolua/9router 9router-sttInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add decolua/9router --skill 9router-stt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/9router-stt .github/skills/9router-stt && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "9router-stt" agent skill from https://github.com/decolua/9router/tree/master/skills/9router-stt into .github/skills/9router-stt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "9router-stt", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add decolua/9router --skill 9router-stt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install decolua/9router 9router-stt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/decolua/9router.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/9router-stt .opencode/skills/9router-stt && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "9router-stt" agent skill from https://github.com/decolua/9router/tree/master/skills/9router-stt into .opencode/skills/9router-stt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "9router-stt", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
9router-stt- GitHub stars
- 31k
- Token cost
- ~914 tokens
- SKILL.md length
- 224 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others.
- Transcribing a recording or voice memo to text
- SKILL.md covers Discover, Endpoint, Examples and Response shape, plus 1 more section
- Calls curl and jq; needs NINEROUTER_KEY
- Generating SRT or VTT subtitles from an audio file
What it does
Requests go to `POST /v1/audio/transcriptions` on a 9Router server, which accepts OpenAI Whisper style multipart form data. The agent first lists speech models at `/v1/models/stt` and checks a model's supported parameters at `/v1/models/info`, then sends the model ID and an audio file (mp3, wav, m4a, webm, ogg or flac) with optional language, prompt, response format and temperature.
Output is JSON text by default; `verbose_json` adds language, duration and timestamped segments, and `srt` or `vtt` return subtitle files. A provider table notes quirks: Groq follows the OpenAI shape, Gemini audio is converted server-side, Deepgram uses token auth, AssemblyAI uploads and polling are handled by the server, and NVIDIA and Hugging Face models are available too. Curl and Node examples are included.
When your agent uses it
- Transcribing a recording or voice memo to text
- Generating SRT or VTT subtitles from an audio file
- Choosing between speech-to-text providers behind one endpoint
Example prompts
- “Transcribe ./recordings/standup.mp3 with a Groq Whisper model and print the text.”
- “Make an SRT subtitle file from interview.wav, language English.”
- “List the speech-to-text models available on my 9Router and pick the Deepgram one.”
Requirements
- A 9Router server, with `NINEROUTER_URL` set (and `NINEROUTER_KEY` when auth is on)
- `curl`
What it can do on your machine
Read from SKILL.md and the folder at commit ce4460e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
curljq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
NINEROUTER_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
9Router Speech-to-Text loads about 914 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 224 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from decolua/9router at commit ce4460e, republished under its MIT licence (© decolua). 224 words, ~914 tokens.
Download SKILL.mdSave it as
.claude/skills/9router-stt/SKILL.md (or your agent's skills folder).- name
- 9router-stt
- description
- Speech-to-text via 9Router /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.
9Router — Speech-to-Text
Requires NINEROUTER_URL (and NINEROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/decolua/9router/refs/heads/master/skills/9router/SKILL.md for setup.
Discover
curl $NINEROUTER_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$NINEROUTER_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 $NINEROUTER_URL/v1/audio/transcriptions (OpenAI Whisper compatible, multipart/form-data)
| Field | Required | Notes |
|---|---|---|
model | yes | from /v1/models/stt |
file | yes | audio file (mp3, wav, m4a, webm, ogg, flac) |
language | no | ISO-639-1 (e.g. en, vi) |
prompt | no | hint text to guide transcription |
response_format | no | json (default) / text / verbose_json / srt / vtt |
temperature | no | 0–1 |
Examples
curl -X POST "$NINEROUTER_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $NINEROUTER_KEY" \
-F "model=openai/whisper-1" \
-F "file=@audio.mp3" \
-F "language=vi"JS (Node):
import { createReadStream } from "node:fs";
const form = new FormData();
form.append("model", "groq/whisper-large-v3-turbo");
form.append("file", new Blob([await (await import("node:fs/promises")).readFile("audio.mp3")]), "audio.mp3");
const r = await fetch(`${process.env.NINEROUTER_URL}/v1/audio/transcriptions`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.NINEROUTER_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
| 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. |
© decolua, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/9router-stt of decolua/9router.
Open the folder on GitHubat commit ce4460e
Compare with similar skills
9Router Speech-to-Text next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| 9Router Speech-to-Text this skilldecolua/9router | 31k | — | ~914 | Automated safety check: Pass | MIT | |
| Keirouter Sttmydisha/keirouter | 147 | — | ~680 | Automated safety check: Pass | MIT | |
| Transcribe Anythingswyxio/skills | 176 | — | ~8.5k | Automated safety check: Pass | MIT | |
| Openai Whisper APIopenclaw/openclaw | 392k | 1 repos | ~518 | Automated safety check: Pass | MIT | |
| Watch Videocoreyhaines31/makerskills | 851 | — | ~3.8k | Automated safety check: Pass | MIT | |
| Openai Whispercoco-research/coco | 513 | — | ~964 | Automated safety check: Pass | Custom licence |
Similar skills
Transcribe Anything
swyxio/skills
Transcribes audio and video files to text using pluggable ASR backends.
Openai Whisper API
openclaw/openclaw
OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1.
Watch Video
coreyhaines31/makerskills
When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports.
Openai Whisper
coco-research/coco
Speech-to-text transcription via OpenAI Whisper. An agent skill from coco-research/coco.
Openai Whisper API
trpc-group/trpc-agent-go
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
More from decolua/9router
All 9 skills in this repo9Router AI Gateway Setup
decolua/9router
Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills.
9Router Chat Completions
decolua/9router
Sends chat and code-generation requests through a 9Router gateway using OpenAI or Anthropic message formats, with streaming and auto-fallback combos.
Embeddings via 9Router
decolua/9router
Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.
9Router Image Generation
decolua/9router
Generates images through a 9Router gateway's image endpoint, with model discovery, the request fields and per-provider quirks for OpenAI, Gemini, MiniMax and others.
9Router Text to Speech
decolua/9router
Turns text into spoken audio through a 9Router server, choosing among voices from OpenAI, ElevenLabs, Deepgram, Edge TTS and other providers.
9Router Video Generation
decolua/9router
Submits text-to-video or image-to-video jobs to xAI Grok Imagine through 9Router, then polls the job and downloads the finished MP4.
Related
Categories
Questions about 9Router Speech-to-Text
What does 9Router Speech-to-Text do?
Transcribes audio files into text or subtitles through 9Router's Whisper-compatible endpoint, using models from OpenAI, Groq, Gemini, Deepgram and others. Requests go to `POST /v1/audio/transcriptions` on a 9Router server, which accepts OpenAI Whisper style multipart form data. The agent first lists speech models at `/v1/models/stt` and checks a model's supported parameters at `/v1/models/info`, then sends the model ID and an audio file (mp3, wav, m4a, webm, ogg or flac) with optional language, prompt, response format and temperature.
When should I use 9Router Speech-to-Text?
9Router Speech-to-Text fits situations like: transcribing a recording or voice memo to text; generating SRT or VTT subtitles from an audio file; choosing between speech-to-text providers behind one endpoint.
How do I install 9Router Speech-to-Text in Claude Code?
Run `npx skills add decolua/9router --skill 9router-stt -a claude-code`. Or copy the skill folder (skills/9router-stt in decolua/9router) into .claude/skills/9router-stt in your project. Claude Code loads it when a task matches its description.
How do I install 9Router Speech-to-Text in Codex?
Run `npx skills add decolua/9router --skill 9router-stt -a codex`. Or copy the skill folder (skills/9router-stt in decolua/9router) into .agents/skills/9router-stt in your project. Codex loads it when a task matches its description.
Can I use 9Router Speech-to-Text in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add decolua/9router --skill 9router-stt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/9router-stt, .gemini/skills/9router-stt, .github/skills/9router-stt and .opencode/skills/9router-stt in your project.
What does 9Router Speech-to-Text need to run?
Going by SKILL.md and its folder, 9Router Speech-to-Text needs the command-line tools its instructions call (curl and jq) and credentials named NINEROUTER_KEY. Our summary lists: A 9Router server, with `NINEROUTER_URL` set (and `NINEROUTER_KEY` when auth is on); `curl`.
Does 9Router Speech-to-Text access the network?
SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is 9Router Speech-to-Text safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does 9Router Speech-to-Text use?
9Router Speech-to-Text is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does 9Router Speech-to-Text use?
About 914 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to 9Router Speech-to-Text?
Skills that share tags, products or a category with 9Router Speech-to-Text: Keirouter Stt (mydisha/keirouter, 147 stars), Transcribe Anything (swyxio/skills, 176 stars), Openai Whisper API (openclaw/openclaw, 392k stars) and Watch Video (coreyhaines31/makerskills, 851 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains 9Router Speech-to-Text?
decolua (a GitHub user) maintains it in decolua/9router, which has 30,536 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.
Source: decolua/9router on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.