Model · OpenAI · Text-To-Speech

OpenAI TTS

OpenAI's general-purpose text-to-speech API. Six preset voices, predictable cost, and tight integration with the rest of the OpenAI stack.

Modality: Text-To-Speech
License: Proprietary (Proprietary)
Released: November 6, 2023
Last verified: May 10, 2026
Runs locally: No

Strengths

Predictable, well-priced API
Quality good enough for most podcast/voiceover use cases
Same API key as the rest of OpenAI

Weaknesses

No voice cloning — six preset voices only
Closed weights
Less expressive than ElevenLabs at the high end

Try it

Where	Type	Notes
OpenAI API	hosted-api	API key required

Used in solutions

Voice transcription for sales calls and customer interviews

Official sources

API docs docs

Change log

May 10, 2026 — Initial entry.
May 10, 2026 — Marked deprecated after verification that GPT-4o mini TTS is OpenAI's current speech generation model.