TTS-1 HD
by OpenAI
OpenAI's legacy high-quality speech model.
TTS-1 HD is optimized for higher-fidelity generated speech using the classic OpenAI voice set.
More details
TTS-1 HD by OpenAI is a standard-speed AI text-to-speech model. TTS-1 HD is optimized for higher-fidelity generated speech using the classic OpenAI voice set. Key capabilities include 78 voices across 7 languages, up to 4,096 characters per request.
TTS-1 HD is priced at $0.04 per 1,000 characters of input text. You can generate speech with TTS-1 HD on idapt.app alongside 200+ AI models in one workspace.
Voices
9 · 1 languagesAny of these voices can be paired with TTS-1 HD. Pick a model for quality and speed, a voice for character and language.
Alloy
Multilingual · Neutral
Ash
Multilingual · Neutral
Coral
Multilingual · Neutral
Echo
Multilingual · Male
Fable
Multilingual · Neutral
Onyx
Multilingual · Male
Nova
Multilingual · Female
Sage
Multilingual · Neutral
Shimmer
Multilingual · Female
Pricing
Cost per 1,000 characters
$0.04
Typical paragraph (~500 chars)
$0.02
Billed on input text length
Capabilities
Speed
Standard: Balanced latency & quality
Emotion Control
Natural delivery only
Max Input
4,096 characters per request
Voices
9 voices · 1 languages
