cd /news/artificial-intelligence/gpt-live-1-1-full-duplex-voice-model… · home › topics › artificial-intelligence › article
[ARTICLE · art-172825] src=developers.openai.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

GPT-Live-1.1: Full-duplex voice model for multilingual conversations

OpenAI released GPT-Live-1.1, a full-duplex voice model that can listen while it speaks, priced at $0.05 per minute for active live sessions and $0.02 per minute for standby WebRTC sessions where inference is paused. OpenAI said GPT-Live-1.1 transcribes speech more accurately than GPT-Live-1 and maintains a more consistent accent and voice across languages, with developers able to describe in plain language when the model should hand a task to a backend for reasoning or tool use. The model accepts and outputs audio and text, supports streaming and function calling but not structured outputs or fine-tuning, and carries separate concurrent-session limits from GPT-Live-1.

key takeaway

GPT-Live-1.1 adds full-duplex listening-while-speaking with more accurate transcription and cross-language voice consistency, billed at $0.05 per active minute and $0.02 per standby minute, with delegation to backend reasoning or tools configured in plain language.

read1 min views4 publishedNov 19, 2026
GPT-Live-1.1: Full-duplex voice model for multilingual conversations
Image: Developers (auto-discovered)
GPT-Live-1.1

`gpt-live-1.1`

Full-duplex voice model for multilingual conversations.

Performance

—

Not specified

Speed

—

Not specified

Price

$0.05

Active

Input

Audio, Text

Output

Audio, Text

GPT-Live-1.1 can listen while it speaks. Compared with GPT-Live-1, it transcribes speech more accurately and maintains a more consistent accent and voice across languages. Describe in plain language when the model should hand a task to your backend for reasoning or tool use.

Learn how to start a voice session, prompt GPT-Live, and configure delegation.

Pricing

Voice sessions are billed by duration. Backend model and tool usage is billed separately. See the

pricing page. Live session duration

Per minute

Active

$0.05

Standby

$0.02

The lower standby rate applies to WebRTC sessions while inference is d. See GPT-Live pricing.

Modalities

Text

Input and output

Image

Not supported

Audio

Input and output

Video

Not supported

Endpoints

Live

v1/live/sessions

Chat Completions

v1/chat/completions

Responses

v1/responses

Realtime

v1/realtime

Realtime translation

v1/realtime/translations

Realtime transcription

v1/realtime/transcription_sessions

Assistants

v1/assistants

Batch

v1/batch

Fine-tuning

v1/fine-tuning

Embeddings

v1/embeddings

Image generation

v1/images/generations

Videos

v1/videos

Image edit

v1/images/edits

Speech generation

v1/audio/speech

Transcription

v1/audio/transcriptions

Translation

v1/audio/translations

Moderation

v1/moderations

Completions (legacy) v1/completions

Features

Streaming

Supported

Function calling Supported

Structured outputs

Not supported

Fine-tuning

Not supported

Predicted outputs

Not supported

Snapshots

Use `gpt-live-1.1` in your API requests.

gpt-live-1.1

Rate limits

GPT-Live-1.1 and GPT-Live-1 have separate concurrent-session limits. Each model’s limit applies across inference regions.

See your organization's limits for the rate limits that apply to your account.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gpt-live-1-1-full-du…] indexed:0 read:1min 2026-11-19 · —