As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/elevenlabs-v3/

# Eleven v3

ElevenLabs. Status: current. Type: speech and audio. Released: 2025-06-03.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| ElevenLabs API | `eleven_v3` | https://api.elevenlabs.io/v1/text-to-speech/{voice_id} | https://elevenlabs.io/docs/models |
| ElevenLabs API (Text to Dialogue) | `eleven_v3` | https://api.elevenlabs.io/v1/text-to-dialogue |  |
| Runway API | `eleven_v3` | https://api.dev.runwayml.com/v1/text_to_speech | https://docs.dev.runwayml.com/guides/models/ |
| Web app |  |  | https://elevenlabs.io/app |

## Pricing

- Per 1K characters: $0.08
- Unit as published: per 1K characters (API)
- Source: https://elevenlabs.io/pricing/api
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: audio
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 92. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from ElevenLabs: Scribe v1 (2025-02-26) https://postcutoff.com/m/elevenlabs-scribe-v1/
- After it from ElevenLabs: Eleven Sound Effects v2 (2025-09) https://postcutoff.com/m/elevenlabs-sound-effects-v2/
- Closed weights; access is hosted only.

## What stands out

- Inline audio tags: Controls delivery with inline tags like [whispers], [laughs], [sighs], [excited]; marketed as 'the most expressive Text to Speech model' at launch. Not marked first: bracketed non-verbal cues existed earlier (e.g. Suno Bark, 2023). Source: https://elevenlabs.io/blog/eleven-v3
- Text to Dialogue (multi-speaker): Dedicated Text to Dialogue API for multi-speaker conversations with natural pacing and interruptions. Source: https://elevenlabs.io/blog/eleven-v3
- GA release with symbol/number normalization (found after launch): GA on 2026-02-02: preferred 72% of the time over alpha; error rate on numbers/symbols/notation cut 68% (15.3% -> 4.9%). Source: https://elevenlabs.io/blog/eleven-v3-is-now-generally-available

## Notes

Alpha announced 2025-06-03 (blog date); API initially via sales, GA across all platforms 2026-02-02. 70+ languages, 5,000 chars/request. Artificial Analysis TTS arena Elo ~1169 (Sept 2026). Professional Voice Clones not supported on v3 (restored in v4). Real-time variant eleven_v3_conversational has its own file. Voice design: eleven_ttv_v3. Superseded in quality by eleven_v4 (2026-09-28) but still current.

Expressive TTS with audio tags; superseded in quality by eleven_v4 but still current.

```bash
curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/$VOICE_ID" -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H "Content-Type: application/json" -d '{"text":"[whispers] Did you hear that?","model_id":"eleven_v3"}' -o out.mp3
```

### Changelog
- 2026-09-29: release date corrected to 2025-06-03 (blog); GA date 2026-02-02, Text to Dialogue, AA Elo added.

Sources: https://elevenlabs.io/docs/models , https://elevenlabs.io/pricing/api , https://elevenlabs.io/blog/eleven-v3 , https://elevenlabs.io/blog/eleven-v3-is-now-generally-available

Model page: https://postcutoff.com/m/elevenlabs-v3/