- Home
- Text-to-speech tools
- OpenAI Text-to-Speech
On the recordRead 7 Oct 202621 facts
OpenAI Text-to-Speech
Plans and prices
TTS-1
$15a month
Text-to-speech model optimized for speed · Speech generation through the Audio API
Read 20 Sep 2026 · developers.openai.com
TTS-1 HD
$30a month
Higher-quality text-to-speech model
Read 20 Sep 2026 · developers.openai.com
GPT-4o Mini TTS API usage
$0.60usage-based
maximum 2,000 input tokens · Free tier not supported
Read 7 Oct 2026 · developers.openai.com
On the record
- API access
- Yesdevelopers.openai.com · read 20 Sep 2026
- API integration
- The guide provides examples using OpenAI SDKs for JavaScript, Python, Go, Java, Ruby, and the command line.developers.openai.com · read 7 Oct 2026
- Commercial use
- Yesdevelopers.openai.com · read 20 Sep 2026
- Custom voices
- An approved custom voice can be created from a speaker’s consent recording and matching audio sample, subject to eligibility and recording requirements.developers.openai.com · read 7 Oct 2026
- Data use and retention
- OpenAI says API Platform data is not used for model training by default and that API inputs and outputs may be retained for up to 30 days, with zero data retention available for eligible endpoints and qualifying use cases.openai.com · read 7 Oct 2026
- Export formats
- mp3,opus,aac,flac,wav,pcmdevelopers.openai.com · read 20 Sep 2026
- Languages
- 57developers.openai.com · read 20 Sep 2026
- Languages
- The TTS model can generate spoken audio in the languages listed in the guide by supplying text in the desired language.developers.openai.com · read 7 Oct 2026
- Maker
- OpenAI describes itself as an AI research and deployment company.openai.com · read 7 Oct 2026
- Maximum input
- 4096developers.openai.com · read 20 Sep 2026
- Model input limit
- The model page states a maximum input size of 2,000 tokens.developers.openai.com · read 7 Oct 2026
- Output formats
- The default response format is MP3, and supported formats include Opus, AAC, FLAC, WAV, and PCM.developers.openai.com · read 7 Oct 2026
- Security
- OpenAI says API Platform data is encrypted at rest with AES-256 and in transit with TLS 1.2 or higher, and that the API Platform is SOC 2 Type 2 audited.openai.com · read 7 Oct 2026
- Speech controls
- With gpt-4o-mini-tts, instructions can control accent, emotional range, intonation, impressions, speech speed, tone, and whispering.developers.openai.com · read 7 Oct 2026
- Speech uses
- The guide lists narrating written blog posts, producing spoken audio in multiple languages, and realtime audio output using streaming as example uses.developers.openai.com · read 7 Oct 2026
- Streaming
- Speech API chunked audio streaming lets playback begin before the complete file is generated.developers.openai.com · read 7 Oct 2026
- User disclosure
- OpenAI usage policies require clear disclosure to end users that the TTS voice they hear is AI-generated and not a human voice.developers.openai.com · read 7 Oct 2026
- Voice cloning
- Yesdevelopers.openai.com · read 20 Sep 2026
