minimax-h3-talking-photoMiniMax H3 Talking Photo turns one portrait image and one voice clip into a talking video, driven by the MiniMax H3 multimodal engine: the person in the photo speaks the audio with frame-accurate lip movement, while identity, outfit, framing and background stay pixel-faithful to the source image. When the audio ends before the clip does, the subject settles into a natural idle — blinking and micro-movement, no looping. Pick 480p or 720p and a fixed length of 5, 10 or 15 seconds; pricing is per clip, not metered: 480p at $0.07 / $0.11 / $0.22 and 720p at $0.13 / $0.22 / $0.44 for 5 / 10 / 15 seconds. Eight aspect ratios (16:9 default, from 21:9 down to 9:16 portrait). The driving audio must fit within the chosen length — we verify at create time and reject with a clear 400 rather than letting the task fail upstream. Only successful generations are charged.
Audio-driven talking video on the H3 multimodal model — lip movement follows the voice frame by frame
The output keeps the exact person, outfit and background of your photo; only the face animates
No per-second metering: 480p from $0.07 and 720p from $0.13 per clip, known before you submit
When the audio ends early the subject idles naturally — blinking, no freeze, no looping
Audio longer than the chosen tier is rejected at create time with a clear 400, never billed and failed upstream
Pick a length that covers your audio — shorter audio ends in a natural idle.
$0.07 per clip (480p · 5s) · charged only on success
Your talking video will appear here
MiniMax H3 Talking Photo is a Video Generation API provided by MiniMax. MiniMax H3 Talking Photo turns one portrait image and one voice clip into a talking video, driven by the MiniMax H3 multimodal engine: the person in the photo speaks the audio with frame-accurate lip movement, while identity, outfit, framing and background stay pixel-faithful to the source image. When the audio ends before the clip does, the subject settles into a natural idle — blinking and micro-movement, no looping. Pick 480p or 720p and a fixed length of 5, 10 or 15 seconds; pricing is per clip, not metered: 480p at $0.07 / $0.11 / $0.22 and 720p at $0.13 / $0.22 / $0.44 for 5 / 10 / 15 seconds. Eight aspect ratios (16:9 default, from 21:9 down to 9:16 portrait). The driving audio must fit within the chosen length — we verify at create time and reject with a clear 400 rather than letting the task fail upstream. Only successful generations are charged. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: 480p · 5s: $0.07, 480p · 10s: $0.11, 480p · 15s: $0.22, 720p · 5s: $0.13, 720p · 10s: $0.22, 720p · 15s: $0.44.
Quickly generate brand promotion videos for ad campaigns and social media marketing.
Create compelling short-form video content for platforms like TikTok, Instagram, and YouTube.
Generate product feature demonstrations and tutorials to improve user conversion.
Produce course explanations, knowledge explainers, and training videos at low cost.
MiniMax H3 Talking Photo is available through APIMODELS at: 480p · 5s: $0.07, 480p · 10s: $0.11, 480p · 15s: $0.22, 720p · 5s: $0.13, 720p · 10s: $0.22, 720p · 15s: $0.44. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same MiniMax H3 Talking Photo model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
On APIMODELS, MiniMax H3 Talking Photo runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Image + Audio、MiniMax H3 Engine、480p / 720p、5 / 10 / 15s、8 Aspect Ratios、Fixed Per-Clip Pricing, and you can weigh it on price and capability against other Video Generation models, then switch by changing a single model-name string — no new account or integration. Browse every Video Generation option with live pricing at apimodels.app/models.
MiniMax H3 Talking Photo supports: Image + Audio、MiniMax H3 Engine、480p / 720p、5 / 10 / 15s、8 Aspect Ratios、Fixed Per-Clip Pricing. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes MiniMax H3 Talking Photo through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.