Proposals concealed
Proposals are currently absent
Proposals concealed
Proposals concealed
Current freelance projects in the category AI Speech & Audio Generation
Project Description It is necessary to create a finished video (3-5 minutes or) with a maximally realistic AI avatar. I provide: the finished text; recording of my voice (or materials for its cloning); photos and/or videos to create an AI avatar that closely resembles me. It is necessary to: create a realistic AI avatar that closely resembles me; use my voice for the narration of the text; accurately convey intonation, speech tempo, pauses, accents, and delivery style; ensure natural facial expressions, lip synchronization, and movements; select or create a realistic modern location (apartment, coworking space, or another suitable interior); edit and deliver a fully finished video.Requirements for the Result Maximum similarity of the AI avatar to me. Natural sound of the voice with correct conveyance of intonation, emotions, speech tempo, and logical pauses. High image quality without noticeable AI artifacts. The video should look as if it was shot on a professional camera, not generated by artificial intelligence.Please indicate in your response Cost and completion time
Project Description: https://docs.google.com/document/d/1JfAXtAgZfYBmY5gRFPb-cjeg6UZZZbI1ijZzVcFdeW8/edit?hl=uk&tab=t.0#heading=h.z0w53nb8s2eg In Brief: 1st video in the following formats: 1) Format 9:16, 15-30 sec 2) Format 16:9, 15-30 sec 3) Format 9:16, 6 sec 4) Format 16:9, 6 sec Total of 4 video files for the first video 2nd video in the following formats: 1) Format 9:16, 15-30 sec 2) Format 16:9, 15-30 sec 3) Format 9:16, 6 sec 4) Format 16:9, 6 sec Total of 4 video files for the second creative A total of 8 video files need to be obtained as a result Please indicate an approximate realistic cost of work in your bids – I will base my decision on it
Deployment and setup locally (on a rented computer) of StabilityMatrix with +ComfyUI with Misha24-10/F5-TTS language module, for creating long MP3 audiobooks from text files. No voice cloning. Simple TTS with standard voices. StabilityMatrix with ComfyUI has already been successfully deployed. Just need to install and configure the workflow F5-TTS with Misha24-10 or a similar Chatterbox.
Needed: Record a video review of the service + add AI voiceover Total required: 1 video - Video of 4-5 minutes 5 videos of 1-2 minutes 4 videos of 15-20 seconds. Please write your estimated cost per minute of work or for the project as a whole. It should be a regular review, example - https://www.loom.com/share/0491ad591813486b8afa22535967c4a0 (just of higher quality)