Eleven Flash v2.5
Eleven Flash v2.5 is ElevenLabs' ultra-fast speech model for realtime use. The model ID is eleven_flash_v2_5.
Provider
ElevenLabs
Model family
ElevenLabs
Text-to-speech
Cost tier
Flash
Status
Current
Why teams choose it
ElevenLabs says Flash v2.5 has a lower API price per character than its higher-latency models
without publishing the dollar rate on the models page.
Enterprise plans can set apply_text_normalization to on
Otherwise, normalize numbers in the calling model before synthesis.
Tradeoffs to know
- Dates, currencies, and phone numbers are not normalized by default.
- It is the fast lane, not the expressive Eleven v3 lane.
Technical specs
- Inputs
- text
- Outputs
- audio
- Capabilities
- low-latency speech, realtime agents, 32 languages
- License
- Proprietary API
- API ID
eleven_flash_v2_5- Source
- https://elevenlabs.io/docs/overview/models
- Character Limit
- 40,000
- Model Latency Ms
- 75
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
ElevenLabs family lineup
Related models
Eleven Flash v2.5 FAQ
What is Eleven Flash v2.5?
Eleven Flash v2.5 is ElevenLabs' ultra-fast speech model for realtime use. The model ID is eleven_flash_v2_5. ElevenLabs documents about 75ms model latency and support for the Multilingual v2 languages plus Hungarian, Norwegian, and Vietnamese. The models page lists a 40,000-character request limit, about 40 minutes. Number normalization is off by default to keep latency low.
When does Eleven Flash v2.5 fit best?
Agents Platform voice
What should teams watch out for with Eleven Flash v2.5?
Dates, currencies, and phone numbers are not normalized by default.
Explore next
Models, tools, and comparisons that connect to this reference.