Skip to main content
ElevenLabs is Bolna’s default voice synthesizer. The eleven_turbo_v2_5 model delivers natural-sounding English speech with the lowest latency of any ElevenLabs model.

​
Quick config

To use your own ElevenLabs account (for voice cloning or custom voices), connect it at platform.bolna.ai/auth/elevenlabs.

​
Supported models

eleven_turbo_v2_5 is the standard choice for production agents. Use eleven_flash_v2_5 when you need the absolute lowest time-to-first-audio. eleven_v3_conversational is ElevenLabs’ most expressive model and supports 74 languages. It ignores speed, style and similarity_boost, and accepts only three temperature values (see below). eleven_v4_turbo is ElevenLabs’ newest model, built for real-time conversation at a median inference latency of about 100 ms. It supports 74 languages in Bolna and takes the same settings as v3. Almost every ElevenLabs voice in Bolna works with it; the few that do not render on v4 are left out of its voice list.

​
Key settings

​
Eleven v3 and v4 Turbo settings

eleven_v3_conversational and eleven_v4_turbo take a narrower set of voice settings than the Turbo v2.5 and Flash models:

​
buffer_size guidance

buffer_size controls the trade-off between first-word latency and audio smoothness:
  • 100–150 — fastest first word; can sound choppy if ElevenLabs response is slow
  • 250 — balanced default; works well for most agents
  • 400+ — smoothest speech; higher latency to first word

​
Choosing a voice

ElevenLabs voices are identified by a voice_id. The voice name field is for reference only — Bolna uses voice_id to select the voice. Browse voices in the ElevenLabs Voice Library. Copy the voice ID from the URL or the voice details panel. Example voices: Pass the name exactly as List voices returns it — suffixes included — as voice, and the matching voice_id. A retired voice fails agent creation with 400 The voice_id '<id>' does not exist in voice_profiles. For a custom or cloned voice, use the voice_id from your ElevenLabs account. See Clone Voices and Import Voices.

​
audio_format by telephony provider

​
FAQ

Use eleven_turbo_v2_5 for most production agents. It has the better quality/latency balance. Use eleven_flash_v2_5 only if your primary constraint is time-to-first-audio and you’ve measured that Turbo is too slow. Use eleven_v3_conversational or eleven_v4_turbo when expressiveness is the priority. eleven_v4_turbo is ElevenLabs’ newest model and is in beta on Bolna; Turbo v2.5 remains the lower-latency option.
eleven_v3_conversational and eleven_v4_turbo ignore speed, style and similarity_boost; the models do not act on them. Only temperature (stability) has an effect, and it accepts three values: 0.0, 0.5 and 1.0. Anything else is rounded to the nearest of those. Use Turbo v2.5 or Flash if you need speed control.
A small number of ElevenLabs voices do not render on v4, so they are left out of the v4 Turbo voice list. They still work on the other ElevenLabs models. Pick another voice, or keep that voice on eleven_v3_conversational or eleven_turbo_v2_5.
In the ElevenLabs dashboard, open any voice and look at the URL — the ID is the path component after /voice/. Alternatively, list voices via the ElevenLabs API. Always store the voice_id, not just the name; names can change.
Yes. Clone your voice in ElevenLabs, connect your ElevenLabs account to Bolna, then set voice_id to your cloned voice’s ID. See Clone Voices.
Increase buffer_size to 350–400. Choppy audio usually means the first audio chunk starts before ElevenLabs has generated enough audio to stream smoothly.