菜单
Speech-to-text via AxonRouter /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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Unified multimodal routing via AxonRouter /v1/unified — single endpoint for text, image, audio, and video with a shared response envelope. Use when the user wants a single API contract for multiple modalities or needs to switch between text/image/audio without changing endpoints.
Chat / code generation via AxonRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through AxonRouter.
Generate vector embeddings via AxonRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
Generate images via AxonRouter /v1/images/generations using OpenAI / Gemini Imagen / DALL-E / FLUX / MiniMax / SDWebUI / ComfyUI / Codex models. Use when the user wants to create, generate, draw, or render an image, picture, or text-to-image (txt2img).
Entry point for AxonRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, STT, embeddings, web search, web fetch, and unified multimodal routing. Use when the user mentions AxonRouter, AXONROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.
Text-to-speech via AxonRouter /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Hyperbolic / Inworld voices. Use when the user wants to convert text to speech, generate audio, voiceover, narrate, or read text aloud.
| name | axonrouter-stt |
| description | Speech-to-text via AxonRouter /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. |
Requires AXONROUTER_URL (and AXONROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/rickicode/axonrouter/refs/heads/main/skills/axonrouter/SKILL.md for setup.
curl $AXONROUTER_URL/v1/models/stt | jq '.data[].id'
# Per-model params (language, response_format, prompt, temperature support)
curl "$AXONROUTER_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).
POST $AXONROUTER_URL/v1/audio/transcriptions (OpenAI Whisper compatible, multipart/form-data)
| Field | Required | Notes |
|---|---|---|
model | yes | from /v1/models/stt |
file | yes | audio file (mp3, wav, m4a, webm, ogg, flac) |
language | no | ISO-639-1 (e.g. en, vi) |
prompt | no | hint text to guide transcription |
response_format | no | json (default) / text / verbose_json / srt / vtt |
temperature | no | 0–1 |
curl -X POST "$AXONROUTER_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AXONROUTER_KEY" \
-F "model=openai/whisper-1" \
-F "file=@audio.mp3" \
-F "language=vi"
JS (Node):
const form = new FormData();
form.append("model", "groq/whisper-large-v3-turbo");
form.append("file", new Blob([await (await import("node:fs/promises")).readFile("audio.mp3")]), "audio.mp3");
const r = await fetch(`${process.env.AXONROUTER_URL}/v1/audio/transcriptions`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.AXONROUTER_KEY}` },
body: form,
});
const { text } = await r.json();
console.log(text);
Python:
from openai import OpenAI
import os
client = OpenAI(base_url=f"{os.environ['AXONROUTER_URL']}/v1", api_key=os.environ["AXONROUTER_KEY"])
with open("audio.mp3", "rb") as f:
transcript = client.audio.transcriptions.create(model="openai/whisper-1", file=f, language="en")
print(transcript.text)
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 | 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 |