eleven_english_sts_v2
ElevenLabsEnglish-only voice changer model (Speech to Speech)
en
10,000 characters / request

Not included: Instant voice cloning · Professional voice cloning · Dubbing Studio · Image and video generation · Team collaboration · SSO
Non-beta output made during a paid subscription keeps its commercial license; upgrading does not retroactively license free-tier output
Creative and API share credits. Speech, music, transcription and sound effects have different rates. Paid balances can reach 3 times the monthly allowance.
Not included: Professional voice cloning · Team collaboration · SSO
Non-beta output made during a paid subscription keeps its commercial license; upgrading does not retroactively license free-tier output
Annual billing · $60 / year
Creative and API share credits. Speech, music, transcription and sound effects have different rates. Paid balances can reach 3 times the monthly allowance.
Not included: Team collaboration · SSO
Non-beta output made during a paid subscription keeps its commercial license; upgrading does not retroactively license free-tier output
Annual billing · $220 / year
Creative and API share credits. Speech, music, transcription and sound effects have different rates. Paid balances can reach 3 times the monthly allowance.
Not included: Team collaboration · SSO
Non-beta output made during a paid subscription keeps its commercial license; upgrading does not retroactively license free-tier output
Annual billing · $990 / year
Creative and API share credits. Speech, music, transcription and sound effects have different rates. Paid balances can reach 3 times the monthly allowance.
Not included: SSO
Non-beta output made during a paid subscription keeps its commercial license; upgrading does not retroactively license free-tier output
Annual billing · $2,990 / year
Creative and API share credits. Speech, music, transcription and sound effects have different rates. Paid balances can reach 3 times the monthly allowance.
Not included: SSO
Non-beta output made during a paid subscription keeps its commercial license; upgrading does not retroactively license free-tier output
Annual billing · $9,900 / year
Creative and API share credits. Speech, music, transcription and sound effects have different rates. Paid balances can reach 3 times the monthly allowance.
| Feature | Free | Starter | Creator | Pro | Scale | Business |
|---|---|---|---|---|---|---|
| Text to speech | Included | Included | Included | Included | Included | Included |
| Speech to text | Included | Included | Included | Included | Included | Included |
| Sound effects | Included | Included | Included | Included | Included | Included |
| Voice changer and voice isolation | Included | Included | Included | Included | Included | Included |
| Music generation | Included | Included | Included | Included | Included | Included |
| API | Included | Included | Included | Included | Included | Included |
| Instant voice cloning | Not included | Included | Included | Included | Included | Included |
| Professional voice cloning | Not included | Not included | Included | Included | Included | Included |
| Dubbing Studio | Not included | Included | Included | Included | Included | Included |
| Image and video generation | Not included | Included | Included | Included | Included | Included |
| Team collaboration | Not included | Not included | Not included | Not included | Included | Included |
| SSO | Not included | Not included | Not included | Not included | Not included | Not included |
Custom credits
English-only voice changer model (Speech to Speech)
en
10,000 characters / request
Ultra-fast model optimized for real-time use (~75ms†)
en
30,000 characters / request
Ultra-fast model optimized for real-time use (~75ms†)
All eleven_multilingual_v2 languages plus: hu , no , vi
40,000 characters / request
State-of-the-art multilingual voice changer model (Speech to Speech)
en , ja , zh , de , hi , fr , ko , pt , it , es , id , nl , tr , fil , pl , sv , bg , ro , ar , cs , el , fi , hr , ms , sk , da , ta , uk , ru
State-of-the-art multilingual voice designer model (Text to Voice)
en , ja , zh , de , hi , fr , ko , pt , it , es , id , nl , tr , fil , pl , sv , bg , ro , ar , cs , el , fi , hr , ms , sk , da , ta , uk , ru
Our lifelike model with rich emotional expression
en , ja , zh , de , hi , fr , ko , pt , it , es , id , nl , tr , fil , pl , sv , bg , ro , ar , cs , el , fi , hr , ms , sk , da , ta , uk , ru
10,000 characters / request
Sound effects generation from text prompts
N/A
Human-like and expressive voice design model (Text to Voice)
70+ languages
First generation low-latency model (outclassed by Flash models)
en
First generation low-latency model (outclassed by Flash models)
en , ja , zh , de , hi , fr , ko , pt , it , es , id , nl , tr , fil , pl , sv , bg , ro , ar , cs , el , fi , hr , ms , sk , da , ta , uk , ru , hu , no , vi
Human-like and expressive speech generation
70+ languages
5,000 characters / request
Our most expressive, realtime speech synthesis model (~280ms†)
70+ languages
Our most emotionally rich, expressive speech synthesis model
90+ languages
10,000 characters / request
Business / Creator / enterprise / Free / Pro / Scale / Starter
Our most expressive, real-time speech synthesis model (~100ms†)
90+ languages
Studio-grade music generation from text prompts. Outclassed by music_v2 and music_v2_5
en , es , de , ja , and more
Studio-grade music generation from text prompts, composition plans and previously generated songs
en , es , de , ja , and more
Our most advanced music model. Studio-grade generation from text prompts, composition plans and previously generated songs, with improved quality and prompt adherence over music_v2
en , es , de , ja , and more
First generation speech recognition (outclassed by v2 models)
90+ languages
State-of-the-art speech recognition model
90+ languages
Speech recognition fine-tuned for clinical audio
90+ languages
Real-time speech recognition model
90+ languages