MiniMax Speech 2.8
MiniMax
- Released
- January 23, 2026
- Data date
- October 3, 2026
- Model class
- Access
MiniMax Speech 2.8 controls expressive speech synthesis through native sound tags and voice cloning from a ten-second reference. The family produces multilingual output and explicitly names Mandarin and Japanese among its supported languages.
The API offers the identifiers speech-2.8-hd and speech-2.8-turbo. MiniMax lists $100 per 1M characters for HD and $60 for Turbo for both synchronous and asynchronous speech synthesis. Voice design and cloning are billed separately.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Speech synthesisSource |
| Access | MiniMax APISource |
| Input | Text and a short reference recordingSource |
| Output | AudioSource |
| API model ID | speech-2.8-hd, speech-2.8-turboSource |
| Voice cloning | High-fidelity cloning from a ten-second referenceSource |
| Languages | Mandarin, Japanese, and additional multilingual speech optionsSource |
| Sound tags | Native sound tags for expressive outputSource |
| Family | Family profile with distinct HD and Turbo API variantsSource |
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
- HD price
- speech-2.8-hd costs $100 per 1M characters, synchronous and asynchronousSource
- Turbo price
- speech-2.8-turbo costs $60 per 1M characters, synchronous and asynchronousSource
- Voice services
- Voice Design $3 and Voice Cloning $1.50 per voice, charged on first synthesis use; preview synthesis is billed separatelySource
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 4 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | quality-benchmarks Original wording MiniMax product MOS 4.42 remains family-level and excluded. Qwen Table 12 provides exact HD comparator rows only; they are retained under variantSpecificFindings and must not be transferred to speech-2.8-turbo or used as a generic family rank. |
| Additional source | MiniMax Speech pricing (retrieved October 3, 2026; October 4, 2026) · MiniMax official pricing · Editorial description reviewed October 3, 2026 |
| Additional source | MiniMax Speech 2.8 announcement (retrieved October 3, 2026; October 4, 2026) · MiniMax Speech 2.8 announcement · Editorial description reviewed October 3, 2026 |
| Additional source | Model metadata (retrieved October 4, 2026) |
| Additional source | Model metadata (retrieved October 4, 2026) |