MiniMax: Speech 2.8 HD
Text to speechMiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.
- Price
- 36,039 Toman per 1,000 characters
- Endpoint
- POST /v1/audio/speech
- Published
- Jul 16, 2026
- Offers
- 45 voices
- Offers
- MP3
- Maker
- MiniMax
Free plan prices, in Toman at today's rate. Plans and prices
Price on each plan
Per character of the text read, in Toman at today's rate; a text of 1,000 characters is about a minute and a half of speech.
| Plan | Price |
|---|---|
| Free | 36,039 Toman per 1,000 characters |
| Pro | 34,562 Toman per 1,000 characters |
| Max | 33,085 Toman per 1,000 characters |
Voices
English_expressive_narratorExpressive narratorEnglish_CalmWomanCalmEnglish_Trustworth_ManTrustworthyEnglish_FriendlyPersonFriendly
45 voices in all: any of them may be asked for by name in the API.
Hear all voicesCall it
curl https://ai.fluxcdn.cloud/api/v1/audio/speech -H "Authorization: Bearer $FLUXCDN_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "minimax/speech-2.8-hd", "input": "سلام! به FluxCDN خوش آمدید.", "voice": "English_expressive_narrator", "response_format": "mp3"}' \
--output speech.mp3
