Post-Cutoff

ElevenLabsEleven v3 familyCurrentSpeech and audioReleased 19 Aug 2026

Eleven v3 Conversational

Real-time variant of Eleven v3 for voice agents.

Model ideleven_v3_conversational

Price$0.04 per 1K characters

Checked29 September 2026

Where it stands

34newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

Before it from ElevenLabs
Eleven Dubbing v228 May 2026
After it from ElevenLabs
Eleven v4 / Eleven v4 Turbo28 Sep 2026
Weights
Closed weights; access is hosted only.

How to call it

2 ways to use Eleven v3 Conversational, with the model id each provider expects.

Providers, model ids, endpoints and docs for Eleven v3 Conversational
ProviderModel idEndpointDocs
ElevenLabs API eleven_v3_conversational https://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream elevenlabs.io
ElevenAgents elevenlabs.io

Pricing

Prices for Eleven v3 Conversational
Per 1K characters$0.04

As published: “per 1K characters (API)”.

Source: elevenlabs.io, checked 29 September 2026.

Specs

Input
Text
Output
Audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
19 August 2026
Status
Current
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Real-time v3 with audio tags

    Brings Eleven v3’s expressive delivery and audio tags to streaming/real-time use at ~280 ms latency (excl. application & network), 70+ languages.

    Source: elevenlabs.io

Notes

GA announced 2026-08-19 (ElevenLabs X post and ElevenLabs Developers YouTube video). Artificial Analysis TTS arena Elo ~1196 (Aug 2026). Superseded for agents by eleven_v4_turbo (2026-09-28, ~100 ms). Exact streaming endpoint shown is the generic TTS stream endpoint; websockets also used in ElevenAgents.

Sources: https://elevenlabs.io/docs/models , https://elevenlabs.io/pricing/api , https://x.com/ElevenLabs/status/2090136227617952145 , https://www.youtube.com/watch?v=pNMYYsO_UBE