Due to popular demand of MiniMax TTS we updated MiniMax API v1 to include audio account information to endpoint GET /features, see audio field.
Experimental API for AI services
MiniMax API v1
Experimental API for popular AI services by useapi.net
🔥2
We’re proud to present the LTX Studio API v1 for LTX Studio, an AI-powered video creation platform developed by Lightricks.
LTX Studio provides access to LTX-Video models capable of generating cost-efficient videos ($0.07 per generation) in near real-time, Google’s Veo model, and the FLUX.1 Kontext model with average costs of $0.03 per generation.
LTX-Video and FLUX.1 Kontext models enforce minimal content moderation and will generate adult content.
EXAMPLES
LTX Studio provides access to LTX-Video models capable of generating cost-efficient videos ($0.07 per generation) in near real-time, Google’s Veo model, and the FLUX.1 Kontext model with average costs of $0.03 per generation.
LTX-Video and FLUX.1 Kontext models enforce minimal content moderation and will generate adult content.
EXAMPLES
Updated Runway API v1 endpoint POST frames/create to support optional parameter num_images, supported values: 1 (default), 4.
Experimental API for AI services
Runway API v1
Experimental API for popular AI services by useapi.net
LTX Studio API v1 endpoint POST videos/veo-create has been updated to support Google’s Veo3 model. Veo3 supports text-to-video generation with automatic sound effects.
The POST videos/veo-create endpoint has breaking changes:
• The audioSFX parameter has been removed
• Asset upload type changed from image to reference-image (use type=reference-image in POST /assets)
Examples.
The POST videos/veo-create endpoint has breaking changes:
• The audioSFX parameter has been removed
• Asset upload type changed from image to reference-image (use type=reference-image in POST /assets)
Examples.
❤1
This media is not supported in your browser
VIEW IN TELEGRAM
MiniMax API v1 updates:
• POST llm now supports the MiniMax-M1 reasoning model, allowing up to 1M-token input and 80K-token output.
• POST videos/create now supports the Hailuo 02 model which generates videos at 768p (6 or 10 seconds) and 1080p (6 seconds) resolutions, features advanced instruction following, handles complex physics (including acrobatics 🤹♀️), and supports native 1080p output.
Example.
• POST llm now supports the MiniMax-M1 reasoning model, allowing up to 1M-token input and 80K-token output.
• POST videos/create now supports the Hailuo 02 model which generates videos at 768p (6 or 10 seconds) and 1080p (6 seconds) resolutions, features advanced instruction following, handles complex physics (including acrobatics 🤹♀️), and supports native 1080p output.
Example.
Kling API v1 updates:
• GET accounts/email now includes balance information showing points, tickets, and total balance
• POST tts/create has been re-enabled after temporary maintenance
• GET accounts/email now includes balance information showing points, tickets, and total balance
• POST tts/create has been re-enabled after temporary maintenance
Experimental API for AI services
Kling API v1
Experimental API for popular AI services by useapi.net
MiniMax quietly released a (beta) music model Music-1.5 https://www.minimax.io/audio/music
It supports AI-generated and custom lyrics, no instrumental as of now, max duration is 90 secs.
Single generation cost is 300 credits / ~$0.01…$0.015 (depending on your plan / top-up option)
It's perhaps just slightly better than TemPolor (arguably) but otherwise can't quite compete with Mureka (not even close imho).
We're not sure if this is something anyone has interest in
If you're interested and planning to use it, please leave a comment so we can decide if we need to invest our time supporting it.
It supports AI-generated and custom lyrics, no instrumental as of now, max duration is 90 secs.
Single generation cost is 300 credits / ~$0.01…$0.015 (depending on your plan / top-up option)
It's perhaps just slightly better than TemPolor (arguably) but otherwise can't quite compete with Mureka (not even close imho).
We're not sure if this is something anyone has interest in
If you're interested and planning to use it, please leave a comment so we can decide if we need to invest our time supporting it.
www.minimax.io/audio
MiniMax Audio | AI Audio Generator - Create Lifelike Speech & Music
Experience MiniMax Audio, your AI Audio Generator. Instantly convert text into lifelike speech with 300+ voices across 32 languages, and generate original, high-quality music. Perfect for voiceovers, soundtracks, multimedia content, and more.
Media is too big
VIEW IN TELEGRAM
Kling API v1 updates:
• Added enable_audio parameter to video generation endpoints for sound effects support:
- POST videos/text2video
- POST videos/image2video-frames
- POST videos/image2video-elements
- POST videos/extend
• Enhanced GET assets/download with fileTypes parameter for selective file format downloads (MP4, MP3, WAV, PNG)
Example
• Added enable_audio parameter to video generation endpoints for sound effects support:
- POST videos/text2video
- POST videos/image2video-frames
- POST videos/image2video-elements
- POST videos/extend
• Enhanced GET assets/download with fileTypes parameter for selective file format downloads (MP4, MP3, WAV, PNG)
Example
MiniMax API v1 groundbreaking agent video templates support:
• Added GET videos/agent-templates endpoint to retrieve available agent video templates
• Added POST videos/agent-create endpoint to create videos using agent templates
Examples
• Added GET videos/agent-templates endpoint to retrieve available agent video templates
• Added POST videos/agent-create endpoint to create videos using agent templates
Examples
11labs_fifty_languages_test.wav
4 MB
We’re excited to announce the release of HeyGen API v1, our latest experimental API for HeyGen, a leading AI video generation platform.
HeyGen specializes in creating realistic AI-generated videos with digital avatars and voices. Our API provides access to HeyGen’s text-to-speech capabilities.
Using a free HeyGen account, you can execute an unlimited number of TTS generations using over 1.5K AI voices, including over 1K ElevenLabs Multilingual v2 voices.
Example
HeyGen specializes in creating realistic AI-generated videos with digital avatars and voices. Our API provides access to HeyGen’s text-to-speech capabilities.
Using a free HeyGen account, you can execute an unlimited number of TTS generations using over 1.5K AI voices, including over 1K ElevenLabs Multilingual v2 voices.
Example
TemPolor API currently not functional, they just released update with the breaking changes which we will need to align with.
We'll take care of it tomorrow or on Monday.
We'll take care of it tomorrow or on Monday.
Kling API v1 updates:
• Updated POST images/kolors to support KOLORS v2.1 for text-to-image generation (in addition to existing v1.5 and v2.0 support)
• Added new POST images/kolors-elements endpoint for generating images with multiple image elements (up to 4 subject images, plus optional scene and style images) using KOLORS v2.0
Example.
• Updated POST images/kolors to support KOLORS v2.1 for text-to-image generation (in addition to existing v1.5 and v2.0 support)
• Added new POST images/kolors-elements endpoint for generating images with multiple image elements (up to 4 subject images, plus optional scene and style images) using KOLORS v2.0
Example.
Runway API v1 added POST gen4/act-two endpoint for Gen-4 Act-Two video creation with driving video and character reference.
Example.
Example.
🔥1