Primary use stated or inferred cautiously from official documentation.
E
ELEVENLABS / eleven_text_to_sound_v3
ElevenLabs SFX v3
ElevenLabs sound effects model available to all workspaces since November 2. It converts text instructions to audio and supports loops through loop. The identifier eleven_text_to_sound_v3 explicitly selects it in the API, without relying on the endpoint’s default model.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | eleven_text_to_sound_v3 |
|---|---|
| Model type | Audio and music |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 02 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text |
| Exit | Audio |
| Context window | Not published |
| maximum output | Between 0.5 and 30 seconds per request |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | ElevenLabs |
Ambience and sound effects design for games, video and interactive experiences. The provider describes improvements when combining instructions and musical or vocal sounds. This is not a transcription or voice-cloning model, nor a guarantee of consistent sonic identity across generations.
The API reference permits durations from 0.5 to 30 seconds and plan-dependent formats. Official texts disagree on the default, so model_id must be set. The reference still describes v2 as the default and its retirement has been announced.
03 / CAPABILITIES
What it can do
Orientation
Ambience and sound effects design for games, video and interactive experiences. The provider describes improvements when combining instructions and musical or vocal sounds. This is not a transcription or voice-cloning model, nor a guarantee of consistent sonic identity across generations.
Context
Not published · Between 0.5 and 30 seconds per request
Tools and integration
Not published
Access
ElevenCreative and Sound Effects API
Input modalities
Text
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Billing depends on the ElevenLabs plan, credits and format. A single USD rate per request or equivalence with text-to-speech pricing has not been verified. Check generated-audio cost and the chosen plan’s commercial usage terms.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
No quantitative scores specific to SFX v3 have been verified. Improvements in instruction following, naturalness and high-frequency clipping are provider claims. Compare identical prompts, duration, loops, artifacts and audio levels over repeated samples before integrating results into a product.
i No verified numeric score for the exact version.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
ElevenLabs SFX v3
Version added to Inferama's verified catalog.
07 / SOURCES