AssistantsCustom voices

Gandr

Use Gandr voices in Vapi through the custom-voice provider

Gandr is a text to speech API built for voice agents. It reads numbers, dates, order IDs and addresses correctly, one engine speaks 23 languages with six voices, and every render carries an inaudible watermark. Audio streams back as it is generated.

Gandr’s /v1/vapi endpoint implements the custom-voice contract described in the Custom TTS guide: it reads the nested message envelope, honours the requested sampleRate (8000, 16000, 22050, 24000 or 44100), and returns raw 16-bit little-endian mono PCM.

A Gandr account and API key are required.
1

Create a Gandr key

Sign up at gandr.ai and copy your API key.

2

Store the key in a Custom Credential

In the Vapi Dashboard, create a Custom Credential holding your Gandr key, following server authentication, so the key never travels in the assistant config.

3

Add Gandr as the voice provider

In the assistant config, set the voice provider to custom-voice and point it at Gandr:

1{
2  "voice": {
3    "provider": "custom-voice",
4    "server": {
5      "url": "https://tts.gandr.ai/v1/vapi",
6      "credentialId": "<your-custom-credential-id>",
7      "timeoutSeconds": 10
8    }
9  }
10}
4

Pick a voice and language

Gandr’s stock voices are gandr-ava, gandr-dane, gandr-jenny, gandr-leo, gandr-lewis and gandr-mia. The default is an English female voice. Any of the 23 languages can be set per request, independent of the voice.

5

Test the call

Run a test call in the dashboard. If you hear audio, you are done. If the call times out, check that the Gandr key in the Custom Credential is active and that https://tts.gandr.ai/v1/vapi answers.

Pricing

See Gandr’s pricing page for current plan and usage pricing.

Full API reference: gandr.ai/docs.