메뉴
Text-to-speech via KeiRouter /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Inworld voices. Use when the user wants to convert text to speech, generate audio, voiceover, narrate, or read text aloud.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions KeiRouter, KEIROUTER_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.
Chat / code generation via KeiRouter 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 KeiRouter.
Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
Generate images via KeiRouter /v1/images/generations using OpenAI DALL-E / Gemini Imagen / FLUX / MiniMax / Stability AI / Fal.ai models. Use when the user wants to create, generate, draw, or render an image, picture, or text-to-image (txt2img).
Speech-to-text via KeiRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
Fetch URL → markdown / text / HTML via KeiRouter /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents. Use when the user wants to scrape a webpage, extract URL content, read article, or convert a URL to markdown.
| name | keirouter-tts |
| description | Text-to-speech via KeiRouter /v1/audio/speech using OpenAI / ElevenLabs / Deepgram / Edge TTS / Google TTS / Inworld voices. Use when the user wants to convert text to speech, generate audio, voiceover, narrate, or read text aloud. |
Requires KEIROUTER_URL (and KEIROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/mydisha/keirouter/main/skills/keirouter/SKILL.md for setup.
# 1) List models
curl $KEIROUTER_URL/v1/models/tts | jq '.data[].id'
# 2) Per-model metadata (params, voicesUrl if voice-by-id)
curl "$KEIROUTER_URL/v1/models/info?id=el/eleven_multilingual_v2"
model field in /v1/audio/speech = voice ID directly (e.g. edge-tts/vi-VN-HoaiMyNeural, el/<voice_id>, or openai/tts-1 model+default voice).
POST $KEIROUTER_URL/v1/audio/speech
| Field | Required | Notes |
|---|---|---|
model | yes | voice ID from /v1/models/tts |
input | yes | text to speak |
Query ?response_format=mp3 (default, raw bytes) or ?response_format=json ({audio: base64, format}).
Save MP3:
curl -X POST "$KEIROUTER_URL/v1/audio/speech" \
-H "Authorization: Bearer $KEIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/tts-1","input":"Hello world"}' \
--output speech.mp3
JS (save file):
import { writeFile } from "node:fs/promises";
const r = await fetch(`${process.env.KEIROUTER_URL}/v1/audio/speech`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.KEIROUTER_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({ model: "el/eleven_multilingual_v2", input: "Hello world" }),
});
await writeFile("speech.mp3", Buffer.from(await r.arrayBuffer()));
Default → raw audio bytes (Content-Type audio/mp3).
?response_format=json:
{ "audio": "SUQzBAAAA...", "format": "mp3" }
| Provider | model format | Notes |
|---|---|---|
| OpenAI | tts-1/alloy (model/voice) or just voice | Default model gpt-4o-mini-tts |
| ElevenLabs | <model_id>/<voice_id> or <voice_id> | Default model eleven_flash_v2_5 |
| Edge TTS | voice id e.g. vi-VN-HoaiMyNeural | noAuth; free |
| Deepgram | aura-asteria-en etc | Token auth |
| Inworld | model/voice | Provider-specific auth |