Flash and Turbo

The four low-latency models, grouped because they accept exactly the same settings: eleven_flash_v2_5, eleven_turbo_v2_5, eleven_flash_v2 and eleven_turbo_v2.

eleven_flash_v2_5 is the usual choice for phone calls: it is multilingual and starts speaking soonest, which is what callers notice. eleven_turbo_v2_5 is multilingual and a little steadier in delivery at slightly higher latency. The two _v2 models are the previous, English-focused generation, kept for assistants already using them.

Reached through the ElevenLabs API with OnCore's own API key, not the LiveKit Inference gateway.

Voice settings are set on the assistant, not in the voice body. Leave every one unset and ElevenLabs' own defaults apply; set any one of them and OnCore sends stability and similarityBoost too, at the same values ElevenLabs defaults to.

Settings#

Every setting is optional. Leave one out and OnCore sends nothing for it, so the Default applies. If invalid is what the provider does with a value it does not accept.

Overriding on a single call#

Return this from your assistant-request webhook to change these settings for one call only. The stored voice is left untouched, and the next call starts from it again.

{
  "data": {
    "overrides": {
      "voice": {
        "settings": {
          "stability": 0.5,
          "similarityBoost": 0.75,
          "speed": 1
        }
      }
    }
  }
}

Send only the keys you want to change: anything you leave out keeps the value the assistant already has. Add "id" beside "settings" to swap the whole voice for another one from your catalogue at the same time.

Two of these have a usable range narrower than the accepted one. stability below 0.3 makes delivery erratic between renders, and a very high similarityBoost introduces audible artifacts. Both are accepted at any value in range, so nothing warns you; tune them by ear on a test call.

style and useSpeakerBoost do not apply to these four models. ElevenLabs accepts both without complaint and then ignores them, so setting one changes nothing and reports nothing. Only Eleven Multilingual v2 honours them.

Next steps#

• eleven_multilingual_v2: the next ElevenLabs model.
• Providers introduction: per-call overrides, and how a wrong value behaves across providers.