Xiaomi MiMo Text-designed fictional voices
MiMo V2.5 TTS Voice Design
Describe an original fictional voice and audition it on your script.
Xiaomi describes MiMo V2.5 TTS Voice Design as creating a voice from a natural-language description. Separate what the character sounds like from the words they should speak.
- Text-designed fictional voices
- Speech audio output
- Non-streaming WAV in Playground
Enter a voice description and a separate script in the Playground. It requests a complete WAV and has no reference-recording field. Describe original voice traits without asking to imitate a real person.
Try this model
Generate speech from text using this model.
mimo-v2.5-tts-voicedesignInput
Generated result
Enter a prompt, choose your settings, and generate.
USD /1M tokens
Pricing
| Group | Input | Output |
|---|---|---|
| default | $0 | $0 |
Public list prices are shown in USD. Final charges may vary by account group and usage tier.
Overview
What is MiMo V2.5 TTS Voice Design?
TokenHot's API guide sends the design description in the user message and the script in the assistant message. Begin with a short line so listeners can compare pace, tone, and clarity before a full read.
Describe traits you can listen for
Specify tone, pace, clarity, and rhythm rather than referencing a real person's identity.
Change one direction at a time
Keep the script fixed while comparing two descriptions.
Check the voice in context
Listen with the scene or product flow before approving a read.
From brief to deliverable
Put MiMo V2.5 TTS Voice Design to work
Interactive experience teams
Audition an original robot guide voice
Describe an approachable delivery with a deliberate pace. Keep the welcome line separate from the description.
- Tools you need
- The TokenHot Playground and a listener who can review the script and recording.
- Keep in mind
- Check intelligibility first. Ask listeners what traits they heard before showing the brief.
View a task brief
In Voice description, enter: Clear, warm, lightly mechanical, with even pauses. In Script, paste the approved welcome line.
Game dialogue teams
Compare two reads for a fictional innkeeper
Keep the character line fixed and vary only the delivery, such as measured and welcoming versus brisk and guarded.
- Tools you need
- The TokenHot Playground and a listener who can review the script and recording.
- Keep in mind
- Compare both reads inside the same game scene before choosing a direction.
View a task brief
In Voice description, describe a fictional innkeeper with a low, steady voice and a welcoming cadence. Paste the approved dialogue into Script. Change the description in a separate trial to compare delivery.
Public information design teams
Choose a speaking pace for a fictional mascot
Compare a measured take with a slightly quicker one. Keep dates and instructions identical in both scripts.
- Tools you need
- The TokenHot Playground and a listener who can review the script and recording.
- Keep in mind
- Have a listener confirm every date and instruction before publishing.
View a task brief
In Voice description, describe an original reassuring mascot with clear diction and measured pauses. Paste the approved announcement with all dates into Script.
Capabilities in context
Key features
| Feature | What you get | Why it matters |
|---|---|---|
| Exact model ID | mimo-v2.5-tts-voicedesign | Use this ID in the TokenHot request. |
| API endpoint | POST /v1/chat/completions | Follow the speech request fields in the model-specific guide. |
| Playground input | Voice description plus script | Describe the fictional voice separately from the words to speak. |
| Reference recording | No recording input | Use Voice Clone for a permitted source recording. |
| Playground output | Non-streaming WAV | The voice-design API guide describes streaming as compatibility mode. |
Xiaomi describes the three MiMo speech models. TokenHot's guide and Playground cover the route and its interface. The scene illustrations were made with ImageGen and do not represent audio results. TokenHot model API · Xiaomi MiMo V2.5 TTS release
Audience & fit
Where MiMo V2.5 TTS Voice Design fits
Interactive experience teams
A welcome-line audition to compare with the character brief.
Game dialogue teams
Two candidate reads with contrasting voice directions.
Public information design teams
One candidate announcement with an approved speaking pace.
Cost context
Plan the cost of a useful result
Use the current route price
Check the live TokenHot price table and the rates that apply to your account.
Listen to a short pilot first
Review a representative passage before generating the full script or a batch of lines.
Count revisions and review
Include regenerated lines and the listening time needed to approve usable audio.
Use the current pricing table for available rates and account groups. Model IDs and prices come from TokenHot’s catalog; provider pricing and subscriptions are separate.
Blog
Related Articles
FAQ
Frequently asked questions
What is MiMo V2.5 TTS Voice Design best suited for?
MiMo V2.5 TTS Voice Design is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.
How is MiMo V2.5 TTS Voice Design priced?
Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.
How can I call MiMo V2.5 TTS Voice Design?
Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.
Do I need an audio sample?
No. Enter a natural-language voice description and a script in the Playground.
Where do the description and script go in the API?
Put the required voice description in the user message and the script in the assistant message for a normal synthesis request.
Can I use a voice preset here?
This route uses a description. Use mimo-v2.5-tts for the preset voice selector.
Can I omit the script?
The Playground requires a script. TokenHot's API guide documents a separate optimize_text_preview setting that can allow the assistant message to be omitted.
What does the Playground return?
It requests a complete WAV for listening after synthesis. The API guide describes streaming compatibility mode rather than low-latency output.
Get started
Build with MiMo V2.5 TTS Voice Design
API