Results for “sitespeakai”

11 skills
microsoft
Podcast Generation
Generate AI-powered podcast-style audio narratives from text using Azure OpenAI's GPT Realtime Mini model via WebSocket, with full-stack implementation from React frontend to Python FastAPI backend.
2.7k · bundle
github
Resemble Detect
Detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using the Resemble AI platform.
36.2k · bundle
rootcastleco
Fal Audio
Text-to-speech and speech-to-text using fal.ai audio models
6
nimoqup046-collab
Daily
Reference for building real-time voice and multimodal AI agents with Pipecat, covering pipelines, speech services, LLMs, transports, and deployment.
2
modbender
Speech Is Cheap Sic Skill
Fast, accurate, and incredibly inexpensive automatic speech-to-text transcription service.
12 · bundle
tianhao909
Sentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
1 · bundle
jeffallan
Websocket Engineer
Build real-time communication systems with WebSockets or Socket.IO, including bidirectional messaging, horizontal scaling with Redis, presence tracking, and room management.
10.4k · bundle
mmehdi0606
Gstack
Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
2 · bundle
diegojcn
Fal Audio
Text-to-speech and speech-to-text using fal.ai audio models
1
qcmuu
Sentencepiece
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.
0 · bundle
ekatasingh1107
Signal Scanner
Search the web for companies showing buying signals matching the agency ICP. Enforces 75/25 geo split and 20 gig + 5 company daily targets.
2 · bundle