OpenAI: GPT Audio

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is …

openai/gpt-audio

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced at $32 per million input tokens and $64 per million output tokens.

Specifications & capabilities

Input
text, audio
Output
text, audio
Context window · tokens
128000
Capabilities
audioInput, multimodal, speechOutput, structuredOutputs, toolCalling
Description source ↗

Published prices

1–2 / 2

openai/gpt-audio ↗

$2.50

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-audio ↗

$10.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

35 / 100

source id
stanfordFMTI
canonical model id
openai/gpt-audio
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
OpenAI
assessment type
organization-level disclosure
metric
disclosure_score
result label
35 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–2 / 2

openRouter ↗

field
context_length
value
128000
normalized value
128000
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
16384
normalized value
16384
scope
source-model
source id
openRouter
confidence
1

Original sources

1–3 / 3

OpenRouter · Model page ↗

GitHub · Catalog ↗

OpenRouter · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace