Back to all models

TTS-1 HD

OpenAI · TTS

Default
Latest in family

Key Metrics

Input Limit

N/A tokens

Output Limit

N/A tokens

Input Cost

$30.00/1M

Output Cost

N/A/1M

Sample API Code

Required Libraries

Notes

Text-to-speech model optimized for quality, converting text to natural sounding spoken audio. Key characteristics: High Performance, Medium Speed. Accessed via the Speech endpoint (e.g., v1/audio/speech). Supports snapshots like 'tts-1-hd' for version locking and consistent behavior. The API usage for this model is not supported under the Free tier.

Capabilities

Text-to-speech
High-definition speech synthesis

Supported Data Types

Input Types

text

Output Types

audio

Strengths & Weaknesses

Exceptional at

High-quality audio generation

Additional Information

Latest Update

Jul 26, 2024

Knowledge Cutoff