yummy-gen-voiceUse when the user wants to synthesise speech or text-to-speech (TTS) audio with Gemini through yummycli, including single-speaker narration, multi-speaker di...
Install via ClawdBot CLI:
clawdbot install yummysource/yummy-gen-voiceGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Sep 10, 2026
Independent podcasters and media teams use the skill to convert scripts into polished single-speaker narration in multiple languages. They can quickly swap voices like Charon (Informative) or Puck (Upbeat) to match episode tone. Output WAV files drop directly into audio editing timelines.
Publishers and edtech platforms synthesize long-form course content and audiobook chapters without hiring voice talent for every title. BCP-47 language flags support localized versions for global learners. Timestamped WAV output simplifies file management across large content libraries.
Product teams embed text-to-speech to read documents, notifications, or UI content aloud for visually impaired users. The CLI's JSON output makes it easy to script batch conversion within backend pipelines. Voice selection allows matching brand tone and clarity requirements.
Creative agencies generate quick voiceover drafts for social ads, radio spots, and product demos. Upbeat voices like Puck or Fenrir suit promotional content, while Sulafat works for warm brand storytelling. Iterating on copy becomes fast and cheap before final studio recording.
Indie game developers and app builders prototype multi-speaker conversations with up to two distinct voices per scene. The [Speaker]: format and --speaker flags make it easy to script back-and-forth dialogue. Final audio can be swapped later while keeping the same pipeline.
A monthly platform that wraps the TTS CLI into a web interface for podcasters, YouTubers, and course creators. Users get voice presets, batch generation, and cloud storage of rendered WAV files. Tiers scale by monthly character volume and voice cloning options.
A metered API that exposes single and multi-speaker synthesis endpoints for product teams building accessibility, e-learning, or voice features. Pricing is based on characters synthesized, with premium rates for higher-quality or rare voices. Enterprise plans add SLAs, concurrency, and private deployment.
A productized service where agencies submit scripts and receive broadcast-ready WAV files within hours, bypassing traditional voice talent booking. Human editors QA output and layer music or sound design as add-ons. Rush delivery and multilingual localization carry premium pricing.
💬 Integration Tip
Always verify credentials with `yummycli auth status --provider gemini` before batch runs, and parse the JSON `output` field rather than assuming a filename. Remember that `--voice` and `--speaker` are mutually exclusive, so pick one routing mode per call.
Scored Sep 10, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.