13 Feb 2026
Voicekiller Updates: Voice Design Improvements, Fixed V3 Inconsistency ....
Voice Design Improvements
Date: 18 Mar, 2026
We have improved Voice Design to make custom voice creation more flexible and easier to refine.
Voice Design now supports 15 languages, making it easier to create voices for multilingual projects and global audiences.
We also added Improve description, which helps expand a simple idea into a clearer, more detailed voice prompt before generating.
Voice descriptions and audio samples
Placeholder examples for this update. Replace the descriptions and sample audio files with the final content later.
Version 1: Raspy and Bitter
A deeply resentful elderly male with a standard American accent. Bitter tone with sudden spikes in energy, speaking at a choppy pace with a raspy, thin timbre, conveying intense frustration and a confrontational vibe.
Version 2: Booming and Authoritative
An authoritative elderly male with a Yorkshire British accent. Furious tone with high energy, speaking at a rapid pace with a heavy, booming timbre, projecting an intimidating presence and overwhelming anger.
Voice 3: Conversational Podcast Host
A warm, approachable 32-year-old female with a relaxed Sydney Australian accent. Conversational tone with dynamic energy, speaking at a natural pace with a smooth, inviting timbre, radiating a friendly and authentic vibe.
Voice 4: Dramatic Storytelling
A captivating elderly male with a soft Edinburgh Scottish accent. Nuanced tone with subdued energy, speaking at a slow pace with a slightly gravelly, deep resonance, drawing the listener into a suspenseful and mysterious atmosphere.
Fixed V3 Inconsistency Issue
Date: 16 Feb, 2026
We just launched Premium mode for V3 voices to fix voice inconsistency and the issue where voices could change over time.
Premium sounds more natural, and the voice stays more consistent.
| Sample | Regular (Old) | Premium (New) |
|---|---|---|
| Sample 1 | 0:00 0:00 | 0:00 0:00 |
| Sample 2 | 0:00 0:00 | 0:00 0:00 |
Added Vocal Sounds for V1 Voices
Date: 16 Feb, 2026
We released Premium V1 voices for Studio users a few months ago. Recently, we also added Vocal Sounds.
It supports these sound effects. (laughs), (chuckle), (coughs), (clear-throat), (groans), (breath), (pant), (inhale), (exhale), (gasps), (sniffs), (sighs), (snorts), (burps), (lip-smacking), (humming), (hissing), (emm), (sneezes).
| Name | Sample |
|---|---|
| (laughs) | 0:00 0:00 |
| (inhale) | 0:00 0:00 |
| (coughs) | 0:00 0:00 |
Improved V2 Voices
Date: 13 Feb 2026
We identified an issue where some V2 voices—primarily used by our Pro users—were not responding correctly to acting instructions. We have updated these voices to ensure they now accurately follow your style and tone commands.
| Voice Name | Older Version | New Version |
|---|---|---|
| Ashton | 0:00 0:00 | 0:00 0:00 |
| Bella | 0:00 0:00 | 0:00 0:00 |
Voice Design
Date: 13 Feb 2026
Studio users can create custom voices using the voice design feature. We are offering unlimited Voice Design at this moment.
Example 1
Speak as a sarcastic, assertive teenage girl: crisp enunciation, controlled volume, with vocal emphasis that conveys disdain and authority.
Example 2
gender: Male. pitch: Low male pitch, generally stable. speed: Deliberate pace, slowing slightly after the initial exclamation. volume: Starts loud, then transitions to a projected conversational volume. age: Middle-aged adult. clarity: High clarity with distinct pronunciation. fluency: Highly fluent. accent: American English. texture: Resonant and slightly gravelly. emotion: Initially commanding, shifting to narrative amusement. tone: Authoritative start, moving to an engaging, descriptive tone. personality: Confident and performative.
9 New Voices (For All Users)
Date: 13 Feb 2026
We have recently added open source Qwen TTS voices. These voices are available for all users. A separate filter is also available for Qwen voices. These voices also support acting instructions.
However, their acting instructions understanding is different, which is why we have added separate instructions for them. You can also include your own instructions as well.
| Name | Audio | Instructions |
|---|---|---|
| Ryan | 0:00 0:00 | Spoke with a very sad and tearful voice. |
| Vivian | 0:00 0:00 | High-pitched, fast-paced, loud volume with a harsh and forceful tone, expressing explosive anger and aggression, suitable for a heated argument. |
Voice Clone Updates
Date: 13 Feb 2026
We have two announcements to make for Voice Clone:
- Voice Clone is available for all users, even for Pro users.
- We have improved the Voice Clone Model.
Note: Please note that only V1 model is available for Pro users.
| Original Sample | Text | Studio Version | Pro Version |
|---|---|---|---|
0:00 0:00 | In a realm where magic flows like rivers and dragons soar through crimson skies, a hero's journey begins with a single step into the unknown. | 0:00 0:00 | 0:00 0:00 |
What's Next?
Date: 13 Feb 2026
We're currently focusing on three major initiatives. These features will be exclusive to Studio plan users and above.
Dubbing Studio
Seamlessly dub your videos into multiple languages while preserving the original voice characteristics.
V3 Voice Stability
We're addressing generation consistency for V3 voices. Expect significant improvements in stability within the week.
Mobile App
Create content on the go with our upcoming mobile application. Access your projects from anywhere.