ElevenLabs · Speech / TTS
Eleven v4 New
ElevenLabs calls it its most emotive model
- Provider
- ElevenLabs
- Family
- Eleven
- Model type
- Speech / TTS
- Official release date
- Sep 28, 2026
- Release type
- New model
- Status
- Generally available
- Previous version
- Eleven v3
- Input
- text
- Output
- audio
- Context window
- Not documented
- Max output
- Not documented
- API model id
eleven_v4- API price (input)
- Not verified
- API price (output)
- Not verified
- Price notes
- Billed in credits/characters, not per token.
- Consumer apps
- —
- Developer API
- ElevenLabs API, ElevenAgents, ElevenCreative
- Free access
- None documented
- Paid access
- —
- Availability
- —
- Licence
- proprietary
Main improvements
- ElevenLabs calls it its most emotive model
- 90+ languages (v3: 70+)
- 10,000 character limit per request
- Real-time variant eleven_v4_turbo (~100 ms)
Best use cases
- Voiceover
- Audiobooks
- Voice agents
Benchmarks
No benchmark results recorded. We only list scores with a source, benchmark version and date.