GPT-4o mini TTS
OpenAI's steerable TTS — control tone and delivery with plain-language instructions
Retired
GPT-4o mini TTS appears to be discontinued or shut down — deprecated Oct 2026; API removal Jan 2027 This page is kept as an archive record and is excluded from search engines.
About
gpt-4o-mini-tts is OpenAI's instruction-steerable text-to-speech model: alongside the text you pass an instructions prompt (e.g. speak like a weary detective) that shapes delivery, across 13 built-in voices with streaming and formats from MP3 to PCM. Pricing is token-based at $0.60 per million text input tokens plus $12 per million audio output tokens, roughly $0.015 per minute of audio. Important caveat: OpenAI deprecated the model on October 1, 2026 and will remove it from the API on January 6, 2027, pointing developers at gpt-realtime-2.1-mini — which runs on the Realtime API rather than the speech endpoint and is not a drop-in replacement. Treat any new integration as a migration plan, not a fresh build.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
No public quality benchmarks; OpenAI positions it as its most capable TTS model (docs)
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Pricing ($0.60/1M text input tokens + $12/1M audio output tokens) verified via multiple sources; Deprecation (Oct 1 2026) and removal (Jan 6 2027) verified and honestly flagged in entry; Release date 2025-03-20 derived from verified snapshot name gpt-4o-mini-tts-2025-03-20.