Skip to content
Model infoModelsSnapshot: 15 Oct 2026

SenseTime / SenseNova speech

SenseNova Audio Fusion (0603)

Speech synthesis with weighted voice blending, 36 system voices and configurable speech delivery.

availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
9 of 20 specification fields collected
Text input limitFewer than 10,000 charactersSee specification notes below
Languages2 listedFull language list in specifications
Input billingNot collectedSenseCore
Output billingNot collectedNo inferred price

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 output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)

Use stream=true with a supported format. URL output forces stream=false. The response section limits streaming to PCM/AAC while the parameter enum omits AAC.

Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Context caching
Not collected
Maximum prompt characters
Fewer than 10,000 charactersSource for Maximum prompt characters (opens in a new tab)

The model card says fewer than 10,000; the API guide says a maximum of 10,000. The boundary is preserved as a conflict.

Output formats
MP3, WAV, PCMSource for Output formats (opens in a new tab)

The request enum lists these three formats; an older-looking response paragraph also mentions AAC/ADTS. AAC support is not inferred.

Audio sample rates
8000 Hz, 16000 Hz, 22050 Hz, 24000 Hz, 32000 Hz, 44100 HzSource for Audio sample rates (opens in a new tab)

The request table allows these rates and mono/stereo; the response paragraph instead describes fixed mono 16 kHz. Verify the selected format on the target deployment.

Voice controls
Speed: 0.5–2.0, Volume: greater than 0, at most 10, Pitch: -12 to +12, Weighted blending of system voicesSource for Voice controls (opens in a new tab)

Access & pricing

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

API model ID
SenseNova-Audio-Fusion-0603
Access
Provider documents service access with an eligible account and API key. No paid inference was performed.
Regions
Regional deployment and account eligibility must be confirmed with the provider.
API endpoint URL
POST https://api.sensenova.cn/v1/audio/ttsSource for API endpoint URL (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

This API page describes stateless requests and says it saves no history or user data. This endpoint-specific statement is not a contractual ZDR guarantee for all SenseNova services.

Read the service policy (opens in a new tab)

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.

SenseCore

SenseNova-Audio-Fusion-0603
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

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

Voice choices

36 voices

Choose a voice within SenseNova Audio Fusion (0603). These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
热情孩童child_reqingChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
正气中年man_zhengqiChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
威严霸总man_weiyanChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
清爽帅哥guy_qingshuangChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
温润暖男guy_wenrunChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
深情男友male_shenqingChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
腼腆男友male_miantianChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)
带货女神woman_daihuoChinese / English service; per-voice language not separately listedSystem voice; blending supported.Voice source (opens in a new tab)

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

Classification is an inference from the named native commercial service or licensed edge release, its official access documentation, and cross-checking the developer’s public-weight inventory. The named service weights were not published in the reviewed inventory. This does not classify every SenseNova model as closed: public U1, U1.5, Vision, SI, MARS, InteractiveOmni and Piccolo releases are excluded.

Classification evidence (opens in a new tab)

Lifecycle dates

Service release3 Jun 2025Source (opens in a new tab)

Sources reviewed