Step 1
Write a Voice Description
Use natural language to specify what you want: gender, age, pitch, speaking style, and accent. You can be as simple as “female, British accent” or as specific as “elderly male, very low pitch, slow, slightly raspy.”
AI Voice Design
VoxCPM2 Voice Design:
Generate Any Voice from Text Description
No microphone or audio sample needed. Just describe the voice you want — "female, low pitch, British accent, calm" — and VoxCPM2 creates a matching speaker from scratch, with multilingual output across 30 languages. If you're new, start with VoxCPM2.
No Audio Required·Infinite Voice Combinations·30 Languages
Loading generator...
From Description to Voice — Hear the Results
Each card is a text-only voice specification — no reference recording is required for VoxCPM2 Voice Design.
Description
Female, Child
Voice Design — no audio reference used
Description
Male, High Pitch, Indian Accent
Voice Design — no audio reference used
Description
Female, Elderly, British Accent
Voice Design — no audio reference used
Description
Male, High Pitch, Elderly
Voice Design — no audio reference used
How VoxCPM2 AI Voice Design Works
Step 2
Use Quick-Select Attribute Tags
Not sure how to phrase it? Use the attribute selector to click-select gender, age, pitch, style, and accent. The selections auto-populate your description — or you can mix manual text with selected tags.
Step 3
Generate Your Custom Voice
Click Generate Speech. VoxCPM2 synthesizes a voice that matches your description — no reference audio, no waiting for training. Download as .wav or use it immediately.
Voice Attributes You Can Control
VoxCPM2 Voice Design gives you direct control over voice dimensions. Mix and match attributes to create a voice that fits your exact use case.
Gender
Controls the fundamental voice character.
Age
Affects voice texture, speed patterns, and natural cadence.
Pitch
Adjust the fundamental frequency of the generated voice independently from gender.
Speaking Style
“Normal” for standard narration; “Whisper” for intimate, close-mic styles.
Live preview
You selected: Pick tags above…
→ Result description: -
All attributes can also be written as free text — describe what you want in any order.
Voice Design vs. Voice Cloning —
Which Should You Use?
Voice Design
When to use
- You don't have a reference recording
- You want to create a fictional or brand voice
- You need a voice with specific characteristics (pitch, accent)
- You want to generate multiple distinct voices quickly
Not ideal for
- ✗Replicating a specific real person's voice
Voice Cloning
When to use
- You have an audio recording of the target voice
- You want to replicate a specific person's voice
- You need cross-lingual output in an existing voice
Not ideal for
- ✗Creating a voice without a reference sample
Who Uses VoxCPM2 AI Voice Design
The friendly mythical God, Zeus, with a huge deep powerful voice. Charming, proud, strong and theatrical.
A low, whispery and assertive female voice with a thick French accent. Cool, composed and seductive, with a hint of mystery.
A calm and husky male warrior with a thick Japanese accent. Soft, whiskey low tone and gentle pacing.
A funny alien from outer space with a ludicrous and annoying voice that gargles in a high pitch tone.
A scary old witch who is sneaky and menacing. Croaky, harsh and shrill with a high-pitch cackle.
A very old, cranky and croaky grandma. Very hoarse, grumpy, shrill and frustrated tone.
VoxCPM2 Pricing Plans for
TTS, Voice Cloning, and Voice Design
Start with transparent credit-based pricing for Text to Speech, Voice Cloning, and Voice Design, then choose the plan that fits your usage.
One-time Credits
Free
$0/one-time
2 credits (≈ 200 characters / 16 seconds)
Included in plan
- 30-Language Multilingual
- Voice Design
- Controllable Cloning + Ultimate Cloning
- 48kHz Studio-Quality Output
- MP3 / WAV export
- ✗Commercial license
- ✗Priority queue
Basic
$9.9/one-time
(one-time)
800 credits (≈ 80,000 characters / 1.8 hours)
$0.012 per credit
Included in plan
- Everything in Free
- Commercial license
- Email support
- Credits never expire
Pro
✨ Most Popular
$29.9/one-time
(one-time · most popular)
3,000 credits (≈ 300,000 characters / 4.5 hours)
$0.009 per credit — save 20% vs Basic
Included in plan
- Everything in Basic
- Early access to new voice models
- Credits never expire
Business
✨ Best Value
$49.9/one-time
(one-time · best value)
6,000 credits (≈ 600,000 characters / 12 hours)
$0.008 per credit — save 50% vs Basic
Included in plan
- Everything in Pro
- Priority generation queue
- Early access to new voice models
- Credits never expire
Credits never expire on any paid plan. Outputs from Basic, Pro, and Business are licensed for commercial use under our Terms.
Choose one-time credits • No subscription or auto-renewal
✓ One-time credit packs✓ Credits never expire✓ Secure payments✓ Email support
Frequently Asked Questions About AI Voice Design
What is VoxCPM2 AI Voice Design?
VoxCPM2 AI Voice Design creates a synthetic voice from a text description alone — no audio sample or recording required. Describe the voice you want (e.g., "female, low pitch, British accent, calm") and VoxCPM2 generates a matching speaker voice from scratch.
Do I need an audio recording to use Voice Design?
No. Voice Design is specifically designed for cases where you don't have any audio. Just describe the voice in text — gender, age, pitch, accent, and style — and VoxCPM2 builds it. If you do have an audio sample, use Voice Cloning instead.
What voice attributes can I control in Voice Design?
You can control gender (male/female), age (child/teen/adult/elderly), pitch (very low to very high), speaking style (normal/whisper), and accent (American, British, Australian, Indian, and more). All attributes can be combined in natural language or selected via click-to-tag interface.
How is Voice Design different from Voice Cloning?
Voice Design creates a new voice from a text description — no audio required. Voice Cloning replicates an existing voice from a short reference recording. Use Voice Design when you want to build a fictional or brand voice; use Voice Cloning when you have a recording of the target speaker.
Is VoxCPM2 Design free?
Yes. Voice Design includes a free starter tier on VoxCPM2. You can also try the full VoxCPM2 suite on our homepage. VoxCPM2 is open source under Apache 2.0, so self-hosting is also an option.
Can I use Voice Design in 30 languages?
Yes. After creating a voice with Voice Design, you can generate speech in any of VoxCPM2’s 30 supported languages using that voice. The voice characteristics you specified carry across language outputs.
Can the generated voice be used commercially?
Paid VoxCPM2 plans include commercial-use rights for hosted outputs. The open-source VoxCPM2 model is released under Apache 2.0 for teams that want to self-host.
READY TO START BUILDING?