Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Vidu (ShengShu) / Vidu Audio

Vidu Audio 1.0

Generates short sound effects and background music from text. A second route accepts timed, overlapping sound events using the same audio1.0 model selector.

availableClosed weightsSound effects generationMusic generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
14 of 29 specification fields collected
Audio output duration2–10 seconds; default 10See specification notes below
Audio formatsNot collectedAwaiting source review
Input billingSee ratesVidu API · international · text
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Maximum prompt characters
1,500Source for Maximum prompt characters (opens in a new tab)

One prompt on text2audio; per sound event on timing2audio. Maximum event count and combined prompt budget are not published.

Output duration
2–10 seconds; default 10Source for Output duration (opens in a new tab)
Seed control
Integer; omitted or zero generates a random seed. Provider describes a fixed seed as deterministic; cross-version reproducibility is not established.Source for Seed control (opens in a new tab)
Request mode
POST a native task; poll /ent/v2/tasks/{id}/creations or supply callback_url. States include created, queueing, processing, success and failed.Source for Request mode (opens in a new tab)
Task callbacks
Processing, success and failed events; failed terminal callback delivery retries up to three times. Validate the documented callback signature.Source for Task callbacks (opens in a new tab)
Timed sound events
Events can overlap. Each event prompt is limited to 1,500 characters; from/to must fall within [0, duration]. The documented string field and placeholder example leave exact event serialization unclear.Source for Timed sound events (opens in a new tab)
Output link expiry
Result URLs expire after 24 hours. This is not a provider-side data deletion promise.Source for Output link expiry (opens in a new tab)
Request quotas
General service guidance: five concurrent tasks per organization, shared by its API keys. Load and account tier may affect concurrency.Source for Request quotas (opens in a new tab)
Usage metering
Per generated audio clip, with two duration tiers. Not speech characters, text tokens or a price per question.Source for Usage metering (opens in a new tab)
Published price
International: USD 0.05 up to 5 seconds, USD 0.10 above 5 through 10 seconds. Mainland labels are strictly “less than 5” and “less than 10”; boundary handling is unresolved.Source for Published price (opens in a new tab)

Regional tariffs are separate, not currency conversions.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Vidu API · international · text

Provider source (opens in a new tab)
API model ID
audio1.0
Access
POST https://api.vidu.com/ent/v2/text2audio; Authorization: Token {your api key}.
Regions
International service; inference residency unverified
Output duration
2–10 seconds; default 10Source for Output duration (opens in a new tab)
Sound event limit
Not collected

Maximum number of timed sound events is not published.

Output formats
Not collected

No generated-audio codec/sample-rate guarantee in the reviewed contract.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Audio generationSound generation · 2–5 seconds1$0.05audio clip up to 5 seconds
Audio generationSound generation · >5–10 seconds2$0.10audio clip above 5 and up to 10 seconds

Rate conditions

  1. 10 credits × USD 0.005 per credit at standard published value. No package discount, promotion or tax included. Maximum-five-second tier. API minimum duration is two seconds.
  2. 20 credits × USD 0.005 per credit at standard published value. No package discount, promotion or tax included. Maximum-ten-second tier; shorter clips use the maximum-five-second tier.
Pricing source (opens in a new tab)

Data & enterprise terms

The general privacy policy describes personal-data storage in Singapore, not an inference-residency or no-training guarantee.

Read the service policy (opens in a new tab)

Vidu API · international · timed

Provider source (opens in a new tab)
API model ID
audio1.0
Access
POST https://api.vidu.com/ent/v2/timing2audio; Authorization: Token {your api key}.
Regions
International service; inference residency unverified
Maximum prompt characters
1,500Source for Maximum prompt characters (opens in a new tab)

Per event, not the total request.

Output duration
2–10 seconds; default 10Source for Output duration (opens in a new tab)
Sound event limit
Not collected

Maximum number of timed sound events is not published.

Output formats
Not collected

No generated-audio codec/sample-rate guarantee in the reviewed contract.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Audio generationSound generation · 2–5 seconds1$0.05audio clip up to 5 seconds
Audio generationSound generation · >5–10 seconds2$0.10audio clip above 5 and up to 10 seconds

Rate conditions

  1. 10 credits × USD 0.005 per credit at standard published value. No package discount, promotion or tax included. Maximum-five-second tier. API minimum duration is two seconds.
  2. 20 credits × USD 0.005 per credit at standard published value. No package discount, promotion or tax included. Maximum-ten-second tier; shorter clips use the maximum-five-second tier.
Pricing source (opens in a new tab)

Data & enterprise terms

The general privacy policy describes personal-data storage in Singapore, not an inference-residency or no-training guarantee.

Read the service policy (opens in a new tab)

Vidu API · mainland China · text

Provider source (opens in a new tab)
API model ID
audio1.0
Access
POST https://api.vidu.cn/ent/v2/text2audio; Authorization: Token {your api key}.
Regions
Mainland China service; inference residency unverified
Output duration
2–10 seconds; default 10Source for Output duration (opens in a new tab)
Sound event limit
Not collected

Maximum number of timed sound events is not published.

Output formats
Not collected

No generated-audio codec/sample-rate guarantee in the reviewed contract.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Audio generationSound generation · <5-second tariff1CN¥0.3125clip in published <5-second tier
Audio generationSound generation · <10-second tariff2CN¥0.625clip in published <10-second tier

Rate conditions

  1. 10 credits × CNY 0.03125 per credit at standard published value. No package discount, promotion or tax included. Provider writes “less than 5 seconds”, not an inclusive maximum. Exact 5-second and 10-second handling remains unverified.
  2. 20 credits × CNY 0.03125 per credit at standard published value. No package discount, promotion or tax included. The two published less-than labels overlap. This is the longer tier as listed; no exact 5/10-second boundary policy is invented.
Pricing source (opens in a new tab)

Data & enterprise terms

Account-specific training use and input-retention terms remain unverified.

Vidu API · mainland China · timed

Provider source (opens in a new tab)
API model ID
audio1.0
Access
POST https://api.vidu.cn/ent/v2/timing2audio; Authorization: Token {your api key}.
Regions
Mainland China service; inference residency unverified
Maximum prompt characters
1,500Source for Maximum prompt characters (opens in a new tab)

Per event, not the total request.

Output duration
2–10 seconds; default 10Source for Output duration (opens in a new tab)
Sound event limit
Not collected

Maximum number of timed sound events is not published.

Output formats
Not collected

No generated-audio codec/sample-rate guarantee in the reviewed contract.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Audio generationSound generation · <5-second tariff1CN¥0.3125clip in published <5-second tier
Audio generationSound generation · <10-second tariff2CN¥0.625clip in published <10-second tier

Rate conditions

  1. 10 credits × CNY 0.03125 per credit at standard published value. No package discount, promotion or tax included. Provider writes “less than 5 seconds”, not an inclusive maximum. Exact 5-second and 10-second handling remains unverified.
  2. 20 credits × CNY 0.03125 per credit at standard published value. No package discount, promotion or tax included. The two published less-than labels overlap. This is the longer tier as listed; no exact 5/10-second boundary policy is invented.
Pricing source (opens in a new tab)

Data & enterprise terms

Account-specific training use and input-retention terms remain unverified.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Vidu API · international · text

audio1.0
Not verified

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How it works
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Minimum reusable input
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Lifetime & refresh
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How to enable it
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Usage fields
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Billing rules
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Limits & data boundaries
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

Vidu API · international · timed

audio1.0
Not verified

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How it works
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Minimum reusable input
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Lifetime & refresh
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How to enable it
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Usage fields
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Billing rules
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Limits & data boundaries
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

Vidu API · mainland China · text

audio1.0
Not verified

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How it works
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Minimum reusable input
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Lifetime & refresh
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How to enable it
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Usage fields
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Billing rules
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Limits & data boundaries
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

Vidu API · mainland China · timed

audio1.0
Not verified

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How it works
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Minimum reusable input
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Lifetime & refresh
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

How to enable it
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Usage fields
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Billing rules
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

Limits & data boundaries
Not collected

No public reusable prompt-cache contract or cached-input discount established. Model-internal latent state and retained dialogue memory are different concepts.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Qualified closed-weight classification inference from the named Vidu hosted model, official API/research descriptions and operator proprietary-service terms. Public client code and inference libraries are not model weights. Exact private/public checkpoint lineage remains unverified.

Classification evidence (opens in a new tab)

Sources reviewed