Media is too big
VIEW IN TELEGRAM
Mureka API v1 updated to support custom vocals (upload your own voice):
• Retrieve a list of vocal samples including the ones you uploaded GET music/vocals.
• Upload mp3 vocal POST files/vocal.
• Delete vocal DEL files/vocal.
EXAMPLE
• Retrieve a list of vocal samples including the ones you uploaded GET music/vocals.
• Upload mp3 vocal POST files/vocal.
• Delete vocal DEL files/vocal.
EXAMPLE
❤1
MiniMax API v1 TTS (text-to-speech) has been updated to support the recently added speech-01-hd High Definition model. This is now the new default model for all TTS audio/ endpoints.
Experimental API for AI services
MiniMax API v1
Experimental API for popular AI services by useapi.net
POLL
Tell us which APIs we should focus on in the next few months ⁉️
• Add support for Kling
• Add support for Sora
• Add support for Pika
• Add support for an AI vendor with a free/low-cost FLUX1 schnell/dev model
• Fix PixVerse (browser-based scraping, $20/1-seat, $10/2+ seat subscription)
• Add support for Suno (browser-based scraping, $20/1-seat, $10/2+ seat subscription)
• Add support for Udio (browser-based scraping, $20/1-seat, $10/2+ seat subscription)
• Suggest something else?
Tell us which APIs we should focus on in the next few months ⁉️
• Add support for Kling
• Add support for Sora
• Add support for Pika
• Add support for an AI vendor with a free/low-cost FLUX1 schnell/dev model
• Fix PixVerse (browser-based scraping, $20/1-seat, $10/2+ seat subscription)
• Add support for Suno (browser-based scraping, $20/1-seat, $10/2+ seat subscription)
• Add support for Udio (browser-based scraping, $20/1-seat, $10/2+ seat subscription)
• Suggest something else?
PixVerse API v2 has been updated to support lip-sync for uploaded videos:
Parameter video_path added to POST videos/lipsync to specify video uploaded via POST /files.
EXAMPLES
Parameter video_path added to POST videos/lipsync to specify video uploaded via POST /files.
EXAMPLES
The MiniMax API v1 endpoint POST videos/create has been updated to support T2V-01-Director model.
This model is added in preview mode, we may need to align it with the official MiniMax API once it is published there.
We have added support for Runway Frames see POST frames/create.
This endpoint will generate 4 images in under 20 seconds on average.
You can run several generations in parallel as well.
EXAMPLES
This endpoint will generate 4 images in under 20 seconds on average.
You can run several generations in parallel as well.
EXAMPLES
Article Mastering Runway Frames featuring a script for batch-generating images using Runway Frames.
The Riffusion API v1 has been added. Riffusion, a San Francisco-based artificial intelligence startup that enables anyone to create original music using AI. The company’s groundbreaking AI, called Fuzz, generates music through spectrogram images of sound rather than simple audio samples.
Riffusion produces songs and instrumental music with high quality and supports a number of languages on par with - or even surpassing - those of Suno and Udio.
EXAMPLES
Riffusion produces songs and instrumental music with high quality and supports a number of languages on par with - or even surpassing - those of Suno and Udio.
EXAMPLES
Experimental API for AI services
Riffusion API v1
Experimental API for popular AI services by useapi.net
👍1