GPT-4o mini TTS

OpenAI's text-to-speech, with instructions that steer delivery ("warm, unhurried, a smile in the voice") on top of voice, language and speed.

id provider "openai"

What it does well

13 voices, marin by default.
Delivery instructions up to 500 characters.

Limits

1,000 characters per clip.

Where to call it

REST APIPOST /v1/ai/speechMCPgenerate_speech

Editor agentgenerateMedia kind "speech"

Chat botsTelegram, WhatsApp and Discord

Vidmoat appVidmoat editor

Try it

curl

curl -X POST https://api.vidmoat.com/v1/ai/speech \
  -H "Authorization: Bearer $VIDMOAT_KEY" \
  -H "Content-Type: application/json" \
  -d '{"provider":"openai","text":"Welcome back. Today we build it in ten minutes.","voiceId":"marin","instructions":"warm and upbeat"}'

A test key answers with a sample and spends nothing. Every parameter and error is in the API reference.

API referencedocs/api/generation/create-speech

GPT-4o mini TTS

What it does well

Limits

Where to call it

Try it

Read more

More speech

Grok TTS