Oral News Broadcast Script is optimized for spoken delivery, rewriting written news material into a script tailored for radio anchors, TV news anchors, podcast hosts, or self-media video presenters. Sentences are kept short, natural pauses are inserted, awkward long phrases and obscure characters are avoided so that voice talent can deliver fluently in one take. The script auto-prepends a familiar opening (e.g. "Good evening listeners") and a sign-off (e.g. "That's all for this segment, thanks for tuning in"), and rewrites numbers into easily-spoken forms ("six thousand two hundred" instead of "6,200") to avoid tongue-twisters like "thirty-two point seven percent". Runs entirely on local, so iterate to fit your show length. The output is ready for direct delivery, can be paired with text_to_speech_byteplus for AI voiceover, or dropped into gemini_omni_flash_1_2 / cheer_video / christmas_video to produce a complete video news package. For written press-release format, use news_report instead. Recommended for radio anchors, news podcasters, self-media news channels, and any internal communication that needs spoken-word style. Prompt example 1: Rewrite as a radio news script: highway officials expect traffic over the Mid-Autumn holiday to rise 12.5% from last year and advise avoiding afternoon departures. Prompt example 2: Write a one-minute podcast news read: the city library now stays open until 9 pm on weekends and adds a 24-hour self-service book drop, starting today. Prompt example 3: Make this easy for an anchor to read in short sentences: the northeast monsoon brings lows near 16°C in the north tomorrow, below 10°C in the mountains; please keep warm. Prompt example 4: Rewrite as an upbeat TV anchor read: our city's Little League team beat its rival 5 to 3 at nationals yesterday, winning its first title in ten years; a homecoming parade is on Saturday. Prompt example 5: Write a radio read with the numbers made easy to say: third-quarter tourist visits reached 1,286,000, up 18.4% year on year, with foreign visitors making up about a fifth. Prompt example 6: Link these three stories into a three-minute morning news segment with natural transitions: a new metro line starts trial runs next month; the city pool reopens; a flower market comes this weekend. Prompt example 7: Write a friendly morning PA announcement for our office: a company-wide fire drill is next Wednesday afternoon; when the alarm sounds, take the stairs to the parking lot, not the elevator. Prompt example 8: Turn this press release into a podcast read for two hosts taking turns: the county now offers rides to medical visits for residents over 70, up to four a month, bookable by phone from today. Prompt example 9: Condense this into a top-of-the-hour bulletin under 30 seconds: from 8 tonight to 6 tomorrow morning, pipe work on Zhongshan Road closes some lanes; drivers should take another route. Prompt example 10: Rewrite this for general listeners and explain the jargon: researchers built a new solid-state battery with about 40% more energy density than lithium batteries; ten minutes of charging gives 300 km. Maximum context window (input and output combined): about 1,048,576 tokens. Maximum output per reply: about 65,536 tokens (model reasoning, if any, counts toward this limit). Maximum total upload size per request: 512MB (all files and message content combined). Accepted document formats: pdf, docx, xlsx, pptx, txt, csv (file content is provided to the model as extracted text). Accepted image formats: heic, heif, jpeg, jpg, png, webp. Maximum number of images: 3600. Maximum size per image: 64MB. Maximum total image size per message: 64MB (text and history share the same request size limit; uploads close to the limit may still be rejected). Image dimensions: at least 200 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Output content formats: Text Pricing: Medium Continuous conversation: Supported AI can make mistakes. Please verify important information.