Speech 2.5 Turbo Preview is MiniMax's low-latency text-to-speech model, with expressive voices and support for many languages.
$0.03
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Characters of text spoken per day on NagaAI, counted since November 2026.
Speech 2.5 Turbo Preview is MiniMax's low-latency text-to-speech model, with expressive voices and support for many languages.
On NagaAI, MiniMax Speech 2.5 Turbo Preview costs about $0.03 per 1k chars. You pay only for what you use, with no subscription.
It takes text as input and returns audio.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough activity data to display a chart
