Skip to main content
kRouter
All providers

Pay-per-token

coqui/

Coqui TTS

Coqui TTS — connect via API key.

github.com

Quick setup

  1. Open the kRouter dashboard at http://localhost:20128

  2. Go to Providers → click Coqui TTS

  3. Paste your API key, click Save

  4. Test the connection

Use in your IDE

Point any OpenAI-compatible client at kRouter using your local API key.

ide configbash
# Endpoint
http://localhost:20128/v1

# API key (from Dashboard → API Keys)
sk-krouter-XXXX

# Model
coqui/<model-id>

How Coqui TTS billing works with kRouter

Coqui TTS is pay-per-token. You bring your own API key and kRouter routes to it, so you keep your own rate limits and billing relationship. kRouter authenticates it via free. 1 model are routable as coqui/<model>.

Through kRouter, Coqui TTS serves text-to-speech, exposed on /v1/audio/speech. Requests reach it through the same local OpenAI-compatible endpoint as every other provider, so switching to or from Coqui TTS is a one-line model change in your client rather than a rewrite.

Coqui TTS models & pricing

These are the model ids kRouter routes to. This provider does not publish per-token rates.

ModelRoute as
Tacotron2 DDC (LJSpeech)coqui/tts_models/en/ljspeech/tacotron2-DDC

Coqui TTS links

Coqui TTS FAQ

Is Coqui TTS free through kRouter?

Coqui TTS is pay-per-token: you bring your own API key and are billed by Coqui TTS at their rates. kRouter adds nothing on top and is free and MIT-licensed.

How do I use Coqui TTS with Claude Code or Cursor?

Connect Coqui TTS in the kRouter dashboard, then point your tool at kRouter's local endpoint (http://localhost:20128/v1) with a kRouter API key. Any OpenAI-compatible client works, and models are addressed as coqui/<model>.

Which Coqui TTS models can kRouter route to?

1 model, including Tacotron2 DDC (LJSpeech). Every one is addressed as coqui/<model> from any client.

What happens when Coqui TTS is rate limited?

kRouter detects the limit, parks that account until its real reset time, and fails over to your next connected account or provider — so the request still completes instead of erroring.