MiniMax Speech 2.8 Turbo
$0.09 /1k chars
- Seven reviewed system voices
- MP3, WAV, FLAC, or PCM output
MiniMax Speech 2.8 Turbo API
Generate downloadable speech with seven reviewed MiniMax system voices through PiAPI's asynchronous Speech 2.8 Turbo API.
MiniMax Speech 2.8 Turbo pricing
Standard price is shown per 1,000 provider-billed characters; final usage can differ from Unicode length.
MiniMax Speech 2.8 Turbo features
A small, explicit text-to-speech contract for production workflows.
Reviewed system voices
Choose from five English and two Mandarin system voices. Custom and cloned voices are not part of this contract.
Downloadable formats
Select MP3, WAV, FLAC, or raw PCM and receive the completed audio_url in that format.
Speed control
Adjust speech speed from 0.5× to 2× for narration and dialogue workflows.
Workspace History
Review completed tasks and download generated audio from the existing History view.
Use MiniMax Speech 2.8 Turbo
Create your API key
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Top up credits
Add credits on the billing page when you are ready to scale beyond the free tier.
Call the API
POST your first task following the API docs, then poll the task until the result is ready.
Iterate in the playground
Prototype prompts and settings in the the playground above before wiring them into your product.
Create a task
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "minimax",
"task_type": "speech-2.8-turbo",
"input": {
"text": "YOUR_PROMPT",
"voice": "English_expressive_narrator",
"response_format": "mp3",
"speed": 1
}
}'Retrieve the result
curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'audio_url
Pricing
- per_1k_characters: $0.09 / 1k_characters
MiniMax Speech 2.8 Turbo FAQ
Which voices are available?
The API exposes five English and two Chinese Mandarin system voices. Custom and cloned voices are not supported.
Which output formats can I download?
Choose MP3, WAV, FLAC, or raw PCM. A completed task returns an audio_url.
How is speech billed?
The standard price is $0.09 per 1,000 provider-billed characters. Provider billing may differ from Unicode character count.
How do I call the API?
Submit a speech-2.8-turbo task, poll its task ID, then download the audio_url when the task is completed.
More questions? See the API docs.