Choose a model for the work you need to doMe
← Model directory

MiniMax speech-01-hd

MiniMax· speech-01-hd

Model specifications and sources

These details come from a baseline model catalog; the provider's specifications have not yet been verified.

Convert text into narration using supported provider voices, including Chinese content.

Context window
Not applicable
Maximum input
Not applicable
Maximum output
Not applicable
Input modalities
Not published / unverified
Output modalities
Not published / unverified
Default snapshot
Not published / unverified
Documentation checked
Unverified
Automatic model identity check
官方本次资料未列出精确型号 ID · 2026-11-11
Next automatic check
2026-11-12T05:24:52.304Z
Identity check source
Official evidence page ↗
Documentation source
View source ↗
Official APIInternationalVersion 2

Convert text into narration using supported provider voices, including Chinese content.

Text to speech
Add to comparison
Changing the channel loads its own configuration
API BASE URLhttps://api.minimax.io/v1
Actual API model IDspeech-01-hd
Request method / pathPOST /t2a_v2
AuthenticationAuthorization: Bearer $API_KEY
Edit request parameters

Edit JSON within the verified parameter ranges. Copy and export stop if types, required fields, or enum values are invalid.

Important upstream changes are under review. New formal configurations are temporarily unavailable. Key configuration fields have not been verified for over 72 hours. Update the sources first.
Template v1.0.0 · Catalog version 2

User experience ratings

Model result satisfaction and provider-channel experience are separate. Channel scores average only the service items each person rated; the platform-only score is independent. Each anonymous identity counts once. Ratings appear immediately; actual use is not verified.

Model result scoreNo ratings yetAcross verified same-version channels; identities count once.

Experience by provider

Model result:No ratings yetChannel service:No ratings yet

MiniMax · MiniMax speech-01-hd

Loading ratings…