Speech 2.5 Turbo Preview: Benchmarks, Pricing & Examples
Speech 2.5 Turbo Preview is a text-to-speech model from MiniMax, released in December 2024, with a 3K-token context window, and pricing from $1.00 per 1M input tokens.
Low latency with emotion support, optimized for speed
Speech 2.5 Turbo Preview pricing
Providers
Speech 2.5 Turbo Preview starts at $1.00 per million input tokens via MiniMax.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 MiniMax | $1.00 | — | — | 2.5K/— | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Speech 2.5 Turbo Preview context window
Input and output token limits for Speech 2.5 Turbo Preview, plus how it ranks on long-context understanding.
Try now
huggleGive your ideas
a voice.
Bring your next story, script, or creative project into your Huggle workspace.
Opens in Huggle
Speech 2.5 Turbo Preview latency
Speech 2.5 Turbo Preview time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Speech 2.5 Turbo Preview license
Speech 2.5 Turbo Preview is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
FAQ
Common questions about Speech 2.5 Turbo Preview.