claudegoodies
Skill

9router-tts

From decolua

Text-to-speech via 9Router /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.

Calls a 9Router /v1/audio/speech HTTP endpoint to convert text into MP3 audio via configurable TTS providers.

Use it when

  • Generating voiceover/narration audio from text in a script or app
  • Need to switch between OpenAI, ElevenLabs, Deepgram, Edge TTS voices via one API
  • Already run a 9Router instance and want TTS access from Claude Code

Skip it if

  • Requires a running 9Router server with NINEROUTER_URL (and key) already configured
  • Just a curl/fetch wrapper around one HTTP endpoint, not a bundled TTS engine
  • Voice IDs and auth vary per provider, requiring manual lookup per call

Facts

Repository
decolua/9router
Status
Actively maintained
Last commit
Source file
skills/9router-tts/SKILL.md

Source preview

The instructions Claude Code reads when this skill runs.

# 9Router — Text-to-Speech

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

```bash
# 1) List models
curl $NINEROUTER_URL/v1/models/tts | jq '.data[].id'
# 2) Per-model metadata (params, voicesUrl if voice-by-id)
curl "$NINEROUTER_URL/v1/models/info?id=el/eleven_multilingual_v2"
# 3) List voices (elevenlabs, edge-tts, deepgram, inworld, local-device). Optional ?lang=vi
curl "$NINEROUTER_URL/v1/audio/voices?provider=edge-tts&lang=vi" | jq '.data[].model'
```

`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).

## Endpoint

`POST $NINEROUTER_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}`).

## Examples

Save MP3:

```bash
curl -X POST "$NINEROUTER_URL/v1/audio/speech" \
  -H "Authorization: Bearer $NINEROUTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/tts-1","input":"Hello world"}' \
  --output speech.mp3
```

JS (save file):

```js
import { writeFile } from "node:fs/promises";
const r = await fetch(`${process.env.N
View full source on GitHub →

Other skills