MiniMax Speech 2.8 HDAI text to speech
MiniMax's studio-quality speech, with emotion and over 30 languages. On Leap, it sits beside 174 other models in one studio.
- Text to speech
- No subscription
- Every top model, one account
- Pay per run, priced before it starts
Listen / A fragrance ad, no product named
0 / 7 s
Read the transcript
It smells like the last train home, rain on warm stone, and a decision you will not regret in the morning.
AI text to speech
MiniMax Speech 2.8 HD at a glance
MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It makes speech from your text.
- Made by
- MiniMax
- Makes
- Speech
- Starts from
- Your text
- Voices
- 17 to choose from
- Text
- Up to 10,000 characters
- Price
- $0.135 per 1,000 characters
- Updated
- October 3, 2026
- 01Write the words, pick a voice
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Pick the right one
MiniMax Speech 2.8 HD and its siblings
| Model | Best for | Length | Price per run |
|---|---|---|---|
| MiniMax Speech 2.8 HD (this page) | MiniMax's studio-quality speech, with emotion and over 30 languages. | – | $0.135 per 1,000 characters |
| MiniMax Music 2.6 | Full songs with vocals from a style prompt and your lyrics. | – | $0.21 |
| MiniMax Music 3 | Songs up to five minutes long from a style prompt and your lyrics. Without lyrics it makes an instrumental. A song can end before the length you ask for, which is what the run is billed. | 1 to 300 seconds | $0.0027 to $0.81 |
| MiniMax Speech 2.8 Turbo | MiniMax Speech 2.8 at a lower price, for volume. | – | $0.081 per 1,000 characters |
Start with an idea
Three ways to try MiniMax Speech 2.8 HD
Side by side
More voice and sound models on Leap
Questions
MiniMax Speech 2.8 HD, answered
- What is MiniMax Speech 2.8 HD?
- MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. MiniMax's studio-quality speech, with emotion and over 30 languages. On Leap it runs in one studio beside every other top model, with one account.
- Which voices can I use?
- 17 voices, among them Wise woman, Friendly person, Inspirational girl, Deep voice man and Calm woman. You can hear each one in the studio before you run it.
- How much text can it read in one run?
- Up to 10,000 characters. You pay for the characters you send, with the price shown before you press go.
- How is it different from MiniMax Music 2.6, MiniMax Music 3 and MiniMax Speech 2.8 Turbo?
- MiniMax Speech 2.8 HD: MiniMax's studio-quality speech, with emotion and over 30 languages. MiniMax Music 2.6: Full songs with vocals from a style prompt and your lyrics. MiniMax Music 3: Songs up to five minutes long from a style prompt and your lyrics. Without lyrics it makes an instrumental. A song can end before the length you ask for, which is what the run is billed. MiniMax Speech 2.8 Turbo: MiniMax Speech 2.8 at a lower price, for volume. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- It costs $0.135 per 1,000 characters. You see the exact price before you press go, and a run that fails costs nothing.
- Is MiniMax Speech 2.8 HD free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. It costs $0.135 per 1,000 characters. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as minimax/speech-2.8-hd, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need a MiniMax account?
- No. Leap sends your request to MiniMax's model and gives you what it makes. One Leap account runs MiniMax Speech 2.8 HD and every other model, in the studio, through the API and from your agents.
Your idea, MiniMax Speech 2.8 HD.
Every run shows its price before it starts, and one that fails costs nothing.
Make it with MiniMax Speech 2.8 HDFor developers
Run MiniMax Speech 2.8 HD from code
- Model ID
- minimax/speech-2.8-hd
- Makes
- Voice and sound
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
Texttext
Text, up to 10,000 characters, required
Voicevoice
Wise woman, Friendly person, Inspirational girl, Deep voice man, Calm woman, Casual guy, Lively girl, Patient man, Young knight, Determined man, Lovely girl, Decent boy, Imposing manner, Elegant man, Abbess, Sweet girl 2, Exuberant girl. Default: Wise woman
Speedsettings.speed
0.5 to 2. Default: 1Speech speed (0.5-2.0)
Pitchsettings.pitch
-12 to 12. Default: 0Voice pitch (-12 to 12)
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "minimax/speech-2.8-hd", "input": { "text": "It smells like the last train home, rain on warm stone, and a decision you will not regret in the morning." } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"