gpt-4o-mini-tts
OpenAI's current text-to-speech model, steerable with natural-language instructions about how a line should be delivered.
- Weights
- Not released
- API
- Yes
- Commercial use
- Vendor states commercial use is permitted
It replaces the older tts-1 and tts-1-hd models, which are still listed at flat per-character prices. There is no voice cloning; you pick from OpenAI's preset voices.
Governed by OpenAI's API terms; output can be used commercially.
Specification
- What it takes in
- text
- What it makes
- audio
- Controls
- style-prompting, emotion-control, streaming-low-latency, speed-control
- Weights
- Not released
- API
- Yes
- Pricing
- $12.00 per 1M audio output tokens (per OpenAI's pricing page audio row). Legacy models on the same page: tts-1 $15.00 per 1M characters, tts-1-hd $30.00 per 1M characters.
- Released or updated
- not established
- Languages
- not established
Strengths
- Instruction-following delivery control without SSML
- Very cheap relative to expressive competitors
- Simple integration if you already use the OpenAI API
- Legacy tts-1 / tts-1-hd still available with flat per-character pricing
Weaknesses
- No voice cloning at all - a hard blocker for talent replication
- Small preset voice roster
- No published latency figure on the pages fetched
- Input token cap per request not confirmed from a vendor page
- Language count not documented on the pages fetched
Best for
- explainer and UI voiceover
- quick scratch tracks
- apps already on the OpenAI stack
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- Third-party sources cite $0.60/1M text input tokens and a 2,000 input-token cap for gpt-4o-mini-tts; the vendor pricing page fetched showed only the $12.00/1M audio output row, so the input price and token cap are recorded as null.
- Third-party sources cite 13 voices; not confirmed on a vendor page, so voice count is not recorded.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
MCP servers that front OpenAI
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
370.ai, AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models
One key, 100+ models, chat with any LLM and generate video, images, speech. Free trial at 370.ai.
-
Adclip
Ad creative generation via MCP, copy and static images from a JSON brief. Keyless.
-
Aetherwave
Music, image, video and audio generation across top AI providers - one key, one credit pool.
-
Aidemo
Narrated, captioned product-demo MP4 from a storyboard.json; re-renders itself in CI at ~$0.
-
ArkRoute, Visual AI API Gateway
Generate images and videos using 28+ visual AI models from OpenAI (GPT Image 2, DALL-E 3), Google (Imagen 4, Veo 3.1), ByteDance (Seedream, Seedance 2.0), and Kuaishou (K
-
Avocado AI
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
gpt-realtime-2.1
OpenAI's speech-to-speech model for live conversation, taking audio in and producing audio out with tool use. A mini variant trades quality for roughl
Voice and speech
OpenAI transcription (gpt-4o-transcribe, gpt-transcribe, Whisper)
A family of speech-to-text models spanning batch and realtime use: Whisper and gpt-4o-transcribe for files, gpt-4o-transcribe-diarize for speaker-sepa
Voice and speech
Azure AI Speech text-to-speech (Neural, Neural HD, MAI voices)
Microsoft's enterprise speech synthesis service, with 200+ prebuilt neural voices across 80+ locales plus tiers for HD voices, multilingual voices, mu
Voice and speech