OpenVoice v2
openvoice-v2MyShell OpenVoice v2. Multilingual zero-shot voice cloning with accurate tone-color reproduction and style/emotion control.
- Price
- ≈ $0.0673/run
- Input → output
- Text → Audio
- Developer
- Community
- Updated
- September 23, 2026
Clone a voice
- 1
Your voice
Voice sample *Record up to 30 s · file up to 60 s, 10 MB10 to 30 seconds of clear speech, one speaker, no music or background noise.
Only your own voice or a voice you have verifiable permission for. Imitating other people without their consent is not allowed, see our Terms of Service.
- 2
Text
Language: EN_NEWEST103 / 4,000 - 3
Listen
about $0.0673 per run, billed by the actual GPU time
Playground
Try OpenVoice v2
Input & output
This run
about $0.0673 · 6.73 credits
$0.2017 (20.17 credits) are reserved at the start; the actual GPU time is billed.
For accounts without a purchase: runs above 2 credits need a top-up.
New here?
10 free credits ($0.10) when you sign up with Google
Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits.
Examples
- Length: 0:03
Prompt
Did you ever hear a folk tale about a giant turtle?
Settings
- language
- EN_NEWEST
- speed
- 1
- Length: 0:05
Prompt
这次旅行我们计划去巴黎欣赏埃菲尔铁塔和卢浮宫的美景
Settings
- language
- ZH
- speed
- 1
- Length: 0:06
Prompt
El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante.
Settings
- language
- ES
- speed
- 1
About OpenVoice v2
OpenVoice v2 is a model by Community in the Text-to-speech category. On Railwail, OpenVoice v2 costs ≈ $0.0673 per run.
Pricing
| Typical run (≈ 49 s on A100 (40GB)) | $0.0673 per run |
|---|---|
| GPU time (A100 (40GB)) | $0.00138 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = $0.01
Cost calculator
Price calculator
Typical according to the provider: about 48.7 s
Total
$6.73
673 credits
Per run
$0.0673 · 6.73 credits
Billed by the actual GPU time; this is an estimate.
API
No verified API example
The public API passes a different input format than this model needs. Use the playground above.
Specifications
- Model ID
openvoice-v2- Developer
- Community
- Category
- Text-to-speech
- Input
- Text
- Output
- Audio
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- September 23, 2026
Input parameters
Inputs and settings from the model's input schema. The example in the API section shows which of them the API accepts.
textrequiredText to synthesize
Type: TextDefault: –Allowed values: up to 4,000 charactersaudiorequiredReference clip to clone; requires consent
Type: –Default: –Allowed values: –speedType: NumberDefault:1Allowed values: –languageType: ChoiceDefault:EN_NEWESTAllowed values: EN_NEWEST, EN, ES, FR, ZH, JP, or KR
Tags
- myshell
- tts
- voice-cloning
- multilingual
- open-source
Use cases
Frequently asked questions
What is OpenVoice v2?
OpenVoice v2 is a model by Community in the Text-to-speech category.
How much does OpenVoice v2 cost on Railwail?
On Railwail, OpenVoice v2 costs ≈ $0.0673 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.
Which settings does OpenVoice v2 support?
According to its input schema, OpenVoice v2 knows these parameters: text (up to 4,000 characters), audio, speed, and language (EN_NEWEST, EN, ES, FR, ZH, JP, or KR).
How fast is OpenVoice v2?
There are not enough measured runs of OpenVoice v2 on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is OpenVoice v2 better than AudioLDM 2?
That depends on the task. OpenVoice v2 (Community) and AudioLDM 2 (Haohe Liu) are both models in the Text-to-speech category. The comparison page shows their prices and specifications side by side.
Compare OpenVoice v2 and AudioLDM 2Comparable models
All in this category- AudioLDM 2Haohe Liu
Latent-diffusion model for general-purpose text-to-audio. Generates speech, music, and sound effects with a unified prior.
- Kokoro TTS 82MCommunity
Open-weights 82M-parameter TTS. Punches above its size class on naturalness benchmarks at a fraction of the inference cost of larger models.
- Parler-TTSCommunity
Hugging Face Parler-TTS Mini. Lightweight TTS conditioned on a natural-language style description for fine-grained control over voice characteristics.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.