ElevenLabsAudio modelActive
SFX v3
Summary
SFX v3 is ElevenLabs' sound effects model, available to every workspace since November 2, 2026, including through the API. It generates sounds from text descriptions. Compared with SFX v2, it follows multi-part instructions more closely and handles prompts that include music or vocals better.
When a duration is specified, the API generates 0.5 to 30 seconds and charges 40 credits per second. Without one, it estimates the length from the prompt. The predecessor eleven_text_to_sound_v2 is deprecated and scheduled for removal on March 1, 2027.
All specifications
Architecture
Input and output
- Maximum generation duration
- 0.5 to 30 seconds when duration is specified. If omitted, the API estimates duration from the prompt.
- Source: Maximum generation duration
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Availability
- Available to every workspace, including the API, since November 2, 2026.
- Source: Availability
API
Further details
- Prompt behavior
- Follows multi-part instructions more closely and handles prompts with music or vocals better than SFX v2. Results vary by prompt.
- Source: Prompt behavior
- Predecessor
- eleven_text_to_sound_v2 is deprecated and is scheduled for removal on March 1, 2027.
- Source: Predecessor
Prices
- Credit cost
- 40 credits per second when duration is specified.Source