Today's top news highlights: The New York State Retirement Fund increased its holdings in Strategy to $50 million. Douyin: Non-financial verified accounts are prohibitedToday's top news highlights: The New York State Retirement Fund increased its holdings in Strategy to $50 million. Douyin: Non-financial verified accounts are prohibited

PA Daily News | Nasdaq to formally apply for 5x23-hour trading; Pryzm and Aether Games announce shutdown

2025/12/16 17:30

Today's top news highlights:

The New York State Retirement Fund increased its holdings in Strategy to $50 million.

Douyin: Non-financial verified accounts are prohibited from posting financial content.

UK regulators launch consultation on new cryptocurrency rules.

Fourteen of the 25 largest banks in the United States are developing Bitcoin products.

Nasdaq will formally apply for 5x23 hour trading.

Grayscale: Bitcoin is expected to reach a new all-time high in the first half of 2026.

Analysis: Among the top 100 cryptocurrencies by market capitalization, 75 have fallen below their 50-day and 200-day moving averages.

Macro

Douyin: Non-financial verified accounts are prohibited from posting financial content.

According to CLS News Agency, Douyin released the "Douyin Community Finance Industry Convention (Trial)" on December 16th, clarifying core governance norms such as account qualifications, content management, and marketing behavior, as well as mechanisms for handling violations and holding individuals accountable, thereby regulating the dissemination of finance-related content. The Convention applies to all accounts on the Douyin community that publish finance-related content, defining governance boundaries from the source. Regarding account qualifications, the Convention encourages creators in the finance field to complete platform-wide financial professional qualification certification and explicitly prohibits uncertified accounts from publishing financial professional content or recommending related services.

UK regulators launch consultation on new cryptocurrency rules.

According to Reuters, the UK's Financial Conduct Authority (FCA) launched a broad consultation on a series of proposed rules for the cryptocurrency industry on Tuesday. This comes a day after the UK government announced it would begin regulating the industry from October 2027. Along with the proposals, the FCA also released a research report showing that the proportion of UK adults holding cryptocurrency has fallen by a third over the past year, from 12% to 8%. The FCA stated on Tuesday that its rules will cover the listing of crypto assets, measures to prevent insider trading and manipulation, standards for cryptocurrency trading platforms, and brokerage rules. The agency is also consulting on prudential requirements, regulations to make cryptocurrency staking risks clearer, better protection for both lenders and borrowers in the cryptocurrency market, and potential financial safeguards for crypto companies to manage risk. The FCA is seeking feedback on its proposals until February 12, 2026. The regulator has pledged to finalize the regulatory framework by the end of next year.

The Hong Kong Securities and Futures Commission (SFC) has added the "Hong Kong Stablecoin Exchange" to its list of suspicious virtual asset trading platforms.

The Hong Kong Securities and Futures Commission (SFC) has added the "Hong Kong Stablecoin Exchange" to its list of suspicious virtual asset trading platforms. The SFC stated that the entity claims to operate a virtual asset trading platform and is suspected of engaging in unlicensed activities or fraudulent activities related to virtual assets. The entity also falsely claims to be "jointly established by the Hong Kong Stock Exchange, the Stock Exchange of Hong Kong, and the Futures Exchange of Hong Kong," when in fact it has no connection with any of the three exchanges.

Fourteen of the 25 largest banks in the United States are developing Bitcoin products.

According to River, 14 of the 25 largest banks in the United States are developing Bitcoin products for their clients.

Sberbank, Russia's largest bank, is testing a range of DeFi products.

According to DL News, Sberbank, Russia's largest bank, stated that it is testing a range of DeFi products given its customers' growing interest in trading and holding cryptocurrencies. Anatoly Popov, Deputy Chairman of the Governing Board of Sberbank, told RBC that the bank will "work with regulators to develop digital asset products," adding, "Sberbank is already testing various DeFi products. We firmly believe that traditional banking and DeFi will soon converge." Popov did not mention specific DeFi protocols. He further noted, "We are not limited to private networks. Sberbank is also working on projects involving the use of public blockchains for specific purposes, such as asset tokenization or establishing connections with DeFi platforms." He stated that the bank is interested in operating on "networks with well-developed infrastructure and robust smart contract tools, such as Ethereum," because networks like Ethereum "offer flexible integration options, ensure transparency, and facilitate access to international markets." Popov concluded, "Tokenized assets are being actively tested globally. Russia is now moving in this direction as well."

Japan's Startale and SBI will launch regulated yen stablecoins.

According to Techinasia, Japanese blockchain infrastructure company Startale Group and Japanese financial group SBI Holdings plan to launch a fully regulated, yen-pegged stablecoin by the second quarter of 2026 to support global settlements. The two companies will collaborate on the development of this digital currency under a new agreement. Shinsei Trust & Banking will be responsible for the issuance and redemption management of the stablecoin, while SBI VC Trade, a licensed cryptocurrency exchange, will handle its circulation. This yen-denominated stablecoin will be issued by a trust bank and is intended for global settlements and institutional use. Startale will be responsible for technology development, while SBI will focus on regulatory compliance and promotion.

Nasdaq will formally apply for 5x23 hour trading.

According to a report by Jinshi citing foreign media, Nasdaq plans to file documents with the U.S. Securities and Exchange Commission on Monday to launch 24/7 stock trading services. Nasdaq plans to extend trading hours for stocks and exchange-traded products (ETPs) from the current 16 hours a day, five days a week, to 23 hours a day. Nasdaq's new "5x23" model will be divided into two main trading sessions: ① Daytime session: From 4:00 AM to 8:00 PM Eastern Time. This session will continue to include pre-market, regular, and after-hours trading sessions, with the opening (9:30 AM) and closing (4:00 PM) bells for the regular trading session retained. ② Night session: From 9:00 PM to 4:00 AM the following day. Trades executed between 9:00 PM and midnight during this session will be considered for the next calendar day. Under the new plan, the trading week will begin at 9:00 PM on Sunday and end at 8:00 PM on Friday after the daytime session.

The number of active Bitcoin addresses has fallen to its lowest level in a year, raising renewed concerns about the demand for block space.

According to The Block, Bitcoin network activity has fallen to its lowest level in 12 months as the year-end approaches, with the 7-day moving average of active addresses dropping to 660,000. While a seasonal slowdown is expected, several network metrics are already showing weakness. Currently, the number of active addresses is at its lowest level since December 2024, when network activity peaked due to the speculative frenzy surrounding Ordinals and Runes. This weak network activity is also putting downward pressure on miners' economics. Miners' daily revenue has fallen from an average of $50 million in the third quarter to approximately $40 million. Almost all of this revenue comes from block subsidies, rather than transaction fees, highlighting the limited demand for Bitcoin block space. An unusual dynamic has emerged in the composition of Bitcoin transactions. Rune transactions now account for a larger proportion of total network transaction volume but contribute only 5% to 10% of total fee revenue, raising concerns about the demand for block space. When half of Bitcoin's transaction throughput generates negligible fees, it indicates a mismatch between network utilization and value creation.

Trump said he would "consider" pardoning the developers of the Bitcoin app Samourai.

According to Decrypt, on Monday, US President Trump said he was willing to consider pardoning Keonne Rodriguez, the convicted developer of the Samourai wallet, noting that he was already aware of the case.

Opinion

Grayscale: Bitcoin is expected to reach a new all-time high in the first half of 2026.

According to Cointelegraph, Grayscale analysts, in their 2026 outlook report released Monday, predicted a recovery in the cryptocurrency market, with surging demand driving Bitcoin to a new all-time high in the first half of 2026. Grayscale stated that on a macro level, the risk of fiat currency devaluation is increasing due to rising public sector debt and its potential impact on long-term inflation. As long as this risk continues to rise, investor demand for Bitcoin and Ethereum is likely to continue to increase. Meanwhile, the regulatory tone in the United States has shifted significantly in recent years, and Grayscale expects Congress to pass bipartisan legislation on cryptocurrency market structures in 2026, consolidating the position of blockchain finance in the US capital market and promoting institutional...

Tom Lee: The crypto market has 200 times its current potential; the best is yet to come.

According to CNBC, Fundstrat co-founder and BitMine chairman Tom Lee stated in an interview: "The best time for cryptocurrency is yet to come. Currently, there are only 4 million Bitcoin wallets holding over $10,000 worth of BTC, while there are 900 million retirement and brokerage accounts globally, each holding approximately $10,000. This means the market potential for cryptocurrency is 200 times greater than it is now. I think there were indeed some concerns about quantum computing in the market before, and there was also a large-scale deleveraging event on October 11th, but fundamentally, the year ended on a very high note."

US SEC Chairman: Cryptocurrencies may become a "powerful tool for financial surveillance," but methods exist that do not sacrifice privacy.

According to The Block, SEC Chairman Paul Atkins stated that he believes there is a path forward that balances national security concerns with individual privacy protections, but warned that excessive government intervention could tip the scales too far. Speaking at the SEC's Cryptocurrency Task Force's sixth cryptocurrency roundtable on Monday, Atkins cautioned that while blockchain is particularly efficient at linking transactions to senders, if misdirected, cryptocurrencies could "become the most powerful financial surveillance architecture ever." Atkins stated, "Indeed, if the government's instinct is to treat every wallet as a broker, every piece of software as an exchange, every transaction as a reportable event, and every protocol as a convenient monitoring node, then the government will turn this ecosystem into a financial panopticon." However, Atkins indicated that there are ways to balance innovation and privacy. He said, "I firmly believe that we can work together to build a framework that ensures technological progress and financial development do not come at the expense of individual freedom."

Project Updates

Pryzm will shut down its mainnet in early January 2026, causing its stock price to plummet by nearly 80%.

The Pryzm team, a yield-generating Layer 1 network, announced that due to the unsustainability of its current economic model, it will be shutting down its Layer 1 mainnet in an orderly manner in early January 2026. Users will need to complete the merging of Yield Tokens and Principal Tokens and initiate the redemption process for Collateral Tokens within the next few days. Pryzm also plans to provide PRYZM holders with a mechanism to burn tokens in exchange for allocations from upcoming Ethereum DeFi projects. Furthermore, according to Coingecko data, the PRYZM token has fallen by nearly 80% in the past 24 hours, with a market capitalization of only approximately $52,657.57.

StraitsX is partnering with the Solana Foundation to bring XSGD and XUSD to Solana in early 2026.

StraitsX has announced a partnership with the Solana Foundation to integrate its Singapore dollar-backed stablecoin XSGD and US dollar-backed stablecoin XUSD onto the Solana blockchain, with a planned launch in early 2026. This integration will leverage Solana's efficient, low-cost network to enable real-time global payments and digital commerce. XSGD and XUSD have already been running on multiple blockchains, accumulating over $18 billion in on-chain transaction volume. This Solana listing will be the first time the Singapore dollar and the US dollar are deeply connected on the same chain, supporting on-chain forex, AMM liquidity, lending markets, and institutional-grade payment flows. StraitsX and the Solana Foundation will also collaborate to promote deep liquidity in DEXs, AMMs, and lending markets, further solidifying Solana's central position in AI-driven on-chain payments and DeFi applications.

The prediction platform Probable is about to launch on BNB Chain, supported by PancakeSwap and YZi Labs.

PancakeSwap announced the launch of Probable, a new on-chain prediction platform incubated by PancakeSwap, focusing on providing a zero-fee, user-friendly, and completely transparent prediction experience. Probable will be exclusively listed on BNB Chain, supporting users in predicting cryptocurrency trends, global events, sporting events, and regional markets. The platform utilizes UMA's Optimistic Oracle to ensure fast, tamper-proof, and economically secure event verification, while also allowing users to deposit any token and automatically convert it to USDT for prediction. PancakeSwap and YZi Labs jointly supported the development of Probable, aiming to bring users an innovative prediction market experience.

Aether Games, a blockchain game studio previously backed by Mysten Labs, has announced its closure.

Aether Games, a blockchain game studio, has announced its official closure. Aether Games stated, "We did everything in our power to maintain Aether's operations. We were fully committed to the card game project, striving to adapt to market changes and adjust our direction, and we made significant efforts to explore a sustainable development path. However, we ultimately failed." Aether Games reflected on several factors that led to the failure: during the token generation event, the dishonesty of numerous KOLs and partners consumed a large amount of liquidity; marketing agencies failed to deliver on their promises, while high ongoing operating costs (including auditing, compliance, and listing fees) continuously drained funds; and recently, they received delisting risk notices from several major exchanges. The project team admitted that at the current stage, they did not see a sustainable business model for crypto games that could support developers in the long term. For security reasons, the project will close its Discord channel and warn users to be wary of fraudulent links and wallet theft attempts related to this event. Previously, in May 2023, AetherGames completed a $4.5 million equity financing round, with Mysten Labs, Polygon, and others participating.

Monad's on-chain transaction fee revenue has been below $5,000 for five consecutive days.

According to Defillama data, Monad's on-chain transaction fee revenue has been below $5,000 for five consecutive days, reaching only $3,824 on December 15th. In contrast, Monad's on-chain transaction fee revenue peaked at $42,300 on November 25th.

PayPal launches PYUSD savings vault on Spark platform

According to The Block, PayPal is launching the PYUSD Savings Vault on its decentralized lending platform Spark, providing its stablecoin users with a new way to generate returns on their holdings at an annualized yield (APY) of 4.25%. The PYUSD Savings Vault's yield is pegged to the Sky Savings Rate, which is funded by revenue from the Sky protocol.

MetaMask adds native support for Bitcoin, further advancing its multi-chain development process.

According to The Block, the Ethereum wallet MetaMask is continuing its multi-chain expansion and now natively supports Bitcoin. MetaMask users can now directly purchase Bitcoin with fiat currency, conduct on-chain Bitcoin network transfers, and exchange native EVM assets and SOL for Bitcoin. The latest version of MetaMask will be the first to support native Segregated Witness (SegWit) addresses, and plans to add support for Taproot addresses "soon."

Important data

Analysis: Among the top 100 cryptocurrencies by market capitalization, 75 have fallen below their 50-day and 200-day moving averages.

According to CoinDesk analysis, 75 of the top 100 cryptocurrencies by market capitalization are trading below their 50-day and 200-day simple moving averages (SMAs), indicating overall weakness in the digital asset market. Bitcoin's price has fallen from its all-time high of over $126,000 in early October to $87,000, driving outflows from the market. Major cryptocurrencies such as Ethereum, Solana, BNB, and XRP are also trading below key moving averages, representing 78% of the $3 trillion crypto market capitalization, further dragging down market sentiment. In contrast, only 29 stocks in the Nasdaq 100 index have shown similar weakness, indicating that tech stocks still have market breadth. Bitcoin typically moves closely with the Nasdaq, amplifying downward volatility during bear markets. Currently, only eight cryptocurrencies are showing oversold conditions on the Relative Strength Index (RSI), including PI, APT, and ALGO, suggesting that most tokens may still have room for further decline.

Ark Invest increased its holdings yesterday in companies such as BitMine, Coinbase, and Circle, as well as its own Bitcoin ETF.

According to The Block, on December 15th, Cathie Wood's Ark Invest purchased $17 million worth of BitMine stock, $16.26 million worth of Coinbase stock, and $10.8 million worth of Circle Internet Group stock through its three ETFs (ARKK, ARKW, and ARKF). Ark also purchased $5.94 million worth of Block Inc. stock, $5.2 million worth of Bullish stock, and $1.24 million worth of the Ark-21Shares Bitcoin ETF.

Huang Licheng's long positions in ETH have been completely liquidated again, with cumulative losses exceeding $22.9 million.

According to Onchain Lens monitoring, as the market continues to decline, Huang Licheng (@machibigbrother)'s long ETH position (25x leverage) has been completely liquidated again. Machi's cumulative losses have now exceeded $22.9 million.

Investment and Financing/Acquisition

AI audio startup Mirelo has raised $41 million in seed funding, led by a16z.

Mirelo announced the completion of a $41 million seed funding round, co-led by Index Ventures and a16z, with participation from Atlantic.vc and TriplePoint Capital. Mirelo focuses on developing AI-based foundational models for video and audio layers, aiming to reshape the audio creation experience in videos and games through generative audio technology. Its video-to-audio model can quickly generate high-quality, synchronized sound effects and provides flexible editing capabilities to meet the in-depth needs of creators.

Space has raised $3 million in funding, aiming to become the first 10x leveraged prediction market on Solana.

Leveraged prediction market Space announced the completion of a $3 million seed and strategic funding round. The round was led by Morningstar Ventures, Arctic Digital, and community platforms Echo, Curated, and Impossible Finance. Space plans to use the funds to build the first 10x leveraged prediction market on the Solana blockchain, aiming to make truth a tradable asset.

Animoca Brands will partner with Siri Group and invest in its subsidiary GROW Digital Wealth

According to its official blog, Animoca Brands announced that it has signed a letter of intent with GROW Investment Group (GROW), an investment and asset management platform. Under the letter of intent, Animoca Brands will establish a strategic partnership with GROW and make an equity investment in GROW Asset Management (HK) Limited. GROW Asset Management (HK) Limited will subsequently be renamed GROW Digital Wealth (GDW) and become GROW's flagship platform. According to the proposed cooperation agreement, Animoca Brands and GROW will develop GDW into Asia's premier digital wealth management platform.

Ripple co-founder Jed McCaleb's space startup Vast is in talks for a $2 billion funding round.

According to Forbes, sources familiar with the matter revealed that Vast, a startup aiming to build the world's first commercial space station, is in talks for a $300 million funding round, valuing the company at $2 billion. The source indicated that Balerion Space Ventures will lead the round, noting that negotiations are ongoing and the figures are subject to change. To date, the company has been primarily self-funded by Jed McCaleb, founder of crypto companies Ripple and Stellar, who has amassed billions of dollars. He has stated his willingness to invest up to $1 billion of his personal wealth. Vast plans to launch its first space station prototype, "Haven-1," in 2026 and begin sending components of its next space station, "Haven-2," in 2028, intended to replace NASA's International Space Station. Previously, in March of this year, Ripple co-founder Jed McCaleb shared Vast's multi-billion dollar space station plans.

Crypto bank Anchorage has acquired Securitize's wealth management division.

According to The Block, Anchorage Digital, the first federally chartered crypto bank in the US, has acquired Securitize For Advisors, the wealth management arm of tokenization company Securitize. The terms of the transaction were not disclosed. This move will help Anchorage expand its financial advisory services for registered investment advisors. Anchorage will absorb the Securitize For Advisors team and front-end platform. According to the announcement, Securitize For Advisors grew by over 4500% in the past year, with record highs in new deposits and net assets under management. Securitize CEO Carlos Domingo noted that its advisory division has been "incredibly successful," but this sale will allow Securitize to focus on its "core business."

Circle will acquire the Interop Labs team and intellectual property; Axelar will remain an independent entity.

According to Cointelegraph, stablecoin issuer Circle has signed an agreement to acquire the Interop Labs team and its proprietary technology, bringing core contributors to the Axelar network into its infrastructure business. The deal, expected to close in early 2026, covers Interop Labs' personnel and proprietary intellectual property, while the Axelar network, its foundation, and the AXL token will remain independent and governed by the community.

Institutional holdings

The New York State Retirement Fund increased its holdings in Strategy to $50 million.

According to BitcoinTreasuries.NET, the New York State Retirement Fund has increased its holdings in Bitcoin finance company Strategy (ticker symbol MSTR) to $50 million.

Nakamoto transferred another 705 BTC to his Kraken loan collateral wallet.

According to Emmett Gallic, Bitcoin treasury company Nakamoto (formerly Kindly MD) has transferred another 705 BTC (worth $60 million) to its Kraken loan collateral wallet, bringing its total collateral assets on Kraken to 3,717 BTC (worth $320 million).

a16z crypto transferred 276,000 COMP to Coinbase Prime

According to on-chain analyst Ember, two hours ago, crypto venture capital firm a16z crypto transferred 276,000 COMP (US$7.6 million) to Coinbase Prime. a16z was the lead investor in Compound, investing 1 million COMP (10% of the total COMP supply) in March 2020. Currently, a16z's on-chain address primarily holds 64 million UNI (US$325 million) and 19.51 million OP (US$5.71 million), with no COMP remaining.

Market Opportunity
TOP Network Logo
TOP Network Price(TOP)
$0.000096
$0.000096$0.000096
0.00%
USD
TOP Network (TOP) Live Price Chart
Disclaimer: The articles reposted on this site are sourced from public platforms and are provided for informational purposes only. They do not necessarily reflect the views of MEXC. All rights remain with the original authors. If you believe any content infringes on third-party rights, please contact service@support.mexc.com for removal. MEXC makes no guarantees regarding the accuracy, completeness, or timeliness of the content and is not responsible for any actions taken based on the information provided. The content does not constitute financial, legal, or other professional advice, nor should it be considered a recommendation or endorsement by MEXC.

You May Also Like

South Korea Launches Innovative Stablecoin Initiative

South Korea Launches Innovative Stablecoin Initiative

The post South Korea Launches Innovative Stablecoin Initiative appeared on BitcoinEthereumNews.com. South Korea has witnessed a pivotal development in its cryptocurrency landscape with BDACS introducing the nation’s first won-backed stablecoin, KRW1, built on the Avalanche network. This stablecoin is anchored by won assets stored at Woori Bank in a 1:1 ratio, ensuring high security. Continue Reading:South Korea Launches Innovative Stablecoin Initiative Source: https://en.bitcoinhaber.net/south-korea-launches-innovative-stablecoin-initiative
Share
BitcoinEthereumNews2025/09/18 17:54
Trump Cancels Tech, AI Trade Negotiations With The UK

Trump Cancels Tech, AI Trade Negotiations With The UK

The US pauses a $41B UK tech and AI deal as trade talks stall, with disputes over food standards, market access, and rules abroad.   The US has frozen a major tech
Share
LiveBitcoinNews2025/12/17 01:00
Summarize Any Stock’s Earnings Call in Seconds Using FMP API

Summarize Any Stock’s Earnings Call in Seconds Using FMP API

Turn lengthy earnings call transcripts into one-page insights using the Financial Modeling Prep APIPhoto by Bich Tran Earnings calls are packed with insights. They tell you how a company performed, what management expects in the future, and what analysts are worried about. The challenge is that these transcripts often stretch across dozens of pages, making it tough to separate the key takeaways from the noise. With the right tools, you don’t need to spend hours reading every line. By combining the Financial Modeling Prep (FMP) API with Groq’s lightning-fast LLMs, you can transform any earnings call into a concise summary in seconds. The FMP API provides reliable access to complete transcripts, while Groq handles the heavy lifting of distilling them into clear, actionable highlights. In this article, we’ll build a Python workflow that brings these two together. You’ll see how to fetch transcripts for any stock, prepare the text, and instantly generate a one-page summary. Whether you’re tracking Apple, NVIDIA, or your favorite growth stock, the process works the same — fast, accurate, and ready whenever you are. Fetching Earnings Transcripts with FMP API The first step is to pull the raw transcript data. FMP makes this simple with dedicated endpoints for earnings calls. If you want the latest transcripts across the market, you can use the stable endpoint /stable/earning-call-transcript-latest. For a specific stock, the v3 endpoint lets you request transcripts by symbol, quarter, and year using the pattern: https://financialmodelingprep.com/api/v3/earning_call_transcript/{symbol}?quarter={q}&year={y}&apikey=YOUR_API_KEY here’s how you can fetch NVIDIA’s transcript for a given quarter: import requestsAPI_KEY = "your_api_key"symbol = "NVDA"quarter = 2year = 2024url = f"https://financialmodelingprep.com/api/v3/earning_call_transcript/{symbol}?quarter={quarter}&year={year}&apikey={API_KEY}"response = requests.get(url)data = response.json()# Inspect the keysprint(data.keys())# Access transcript contentif "content" in data[0]: transcript_text = data[0]["content"] print(transcript_text[:500]) # preview first 500 characters The response typically includes details like the company symbol, quarter, year, and the full transcript text. If you aren’t sure which quarter to query, the “latest transcripts” endpoint is the quickest way to always stay up to date. Cleaning and Preparing Transcript Data Raw transcripts from the API often include long paragraphs, speaker tags, and formatting artifacts. Before sending them to an LLM, it helps to organize the text into a cleaner structure. Most transcripts follow a pattern: prepared remarks from executives first, followed by a Q&A session with analysts. Separating these sections gives better control when prompting the model. In Python, you can parse the transcript and strip out unnecessary characters. A simple way is to split by markers such as “Operator” or “Question-and-Answer.” Once separated, you can create two blocks — Prepared Remarks and Q&A — that will later be summarized independently. This ensures the model handles each section within context and avoids missing important details. Here’s a small example of how you might start preparing the data: import re# Example: using the transcript_text we fetched earliertext = transcript_text# Remove extra spaces and line breaksclean_text = re.sub(r'\s+', ' ', text).strip()# Split sections (this is a heuristic; real-world transcripts vary slightly)if "Question-and-Answer" in clean_text: prepared, qna = clean_text.split("Question-and-Answer", 1)else: prepared, qna = clean_text, ""print("Prepared Remarks Preview:\n", prepared[:500])print("\nQ&A Preview:\n", qna[:500]) With the transcript cleaned and divided, you’re ready to feed it into Groq’s LLM. Chunking may be necessary if the text is very long. A good approach is to break it into segments of a few thousand tokens, summarize each part, and then merge the summaries in a final pass. Summarizing with Groq LLM Now that the transcript is clean and split into Prepared Remarks and Q&A, we’ll use Groq to generate a crisp one-pager. The idea is simple: summarize each section separately (for focus and accuracy), then synthesize a final brief. Prompt design (concise and factual) Use a short, repeatable template that pushes for neutral, investor-ready language: You are an equity research analyst. Summarize the following earnings call sectionfor {symbol} ({quarter} {year}). Be factual and concise.Return:1) TL;DR (3–5 bullets)2) Results vs. guidance (what improved/worsened)3) Forward outlook (specific statements)4) Risks / watch-outs5) Q&A takeaways (if present)Text:<<<{section_text}>>> Python: calling Groq and getting a clean summary Groq provides an OpenAI-compatible API. Set your GROQ_API_KEY and pick a fast, high-quality model (e.g., a Llama-3.1 70B variant). We’ll write a helper to summarize any text block, then run it for both sections and merge. import osimport textwrapimport requestsGROQ_API_KEY = os.environ.get("GROQ_API_KEY") or "your_groq_api_key"GROQ_BASE_URL = "https://api.groq.com/openai/v1" # OpenAI-compatibleMODEL = "llama-3.1-70b" # choose your preferred Groq modeldef call_groq(prompt, temperature=0.2, max_tokens=1200): url = f"{GROQ_BASE_URL}/chat/completions" headers = { "Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json", } payload = { "model": MODEL, "messages": [ {"role": "system", "content": "You are a precise, neutral equity research analyst."}, {"role": "user", "content": prompt}, ], "temperature": temperature, "max_tokens": max_tokens, } r = requests.post(url, headers=headers, json=payload, timeout=60) r.raise_for_status() return r.json()["choices"][0]["message"]["content"].strip()def build_prompt(section_text, symbol, quarter, year): template = """ You are an equity research analyst. Summarize the following earnings call section for {symbol} ({quarter} {year}). Be factual and concise. Return: 1) TL;DR (3–5 bullets) 2) Results vs. guidance (what improved/worsened) 3) Forward outlook (specific statements) 4) Risks / watch-outs 5) Q&A takeaways (if present) Text: <<< {section_text} >>> """ return textwrap.dedent(template).format( symbol=symbol, quarter=quarter, year=year, section_text=section_text )def summarize_section(section_text, symbol="NVDA", quarter="Q2", year="2024"): if not section_text or section_text.strip() == "": return "(No content found for this section.)" prompt = build_prompt(section_text, symbol, quarter, year) return call_groq(prompt)# Example usage with the cleaned splits from Section 3prepared_summary = summarize_section(prepared, symbol="NVDA", quarter="Q2", year="2024")qna_summary = summarize_section(qna, symbol="NVDA", quarter="Q2", year="2024")final_one_pager = f"""# {symbol} Earnings One-Pager — {quarter} {year}## Prepared Remarks — Key Points{prepared_summary}## Q&A Highlights{qna_summary}""".strip()print(final_one_pager[:1200]) # preview Tips that keep quality high: Keep temperature low (≈0.2) for factual tone. If a section is extremely long, chunk at ~5–8k tokens, summarize each chunk with the same prompt, then ask the model to merge chunk summaries into one section summary before producing the final one-pager. If you also fetched headline numbers (EPS/revenue, guidance) earlier, prepend them to the prompt as brief context to help the model anchor on the right outcomes. Building the End-to-End Pipeline At this point, we have all the building blocks: the FMP API to fetch transcripts, a cleaning step to structure the data, and Groq LLM to generate concise summaries. The final step is to connect everything into a single workflow that can take any ticker and return a one-page earnings call summary. The flow looks like this: Input a stock ticker (for example, NVDA). Use FMP to fetch the latest transcript. Clean and split the text into Prepared Remarks and Q&A. Send each section to Groq for summarization. Merge the outputs into a neatly formatted earnings one-pager. Here’s how it comes together in Python: def summarize_earnings_call(symbol, quarter, year, api_key, groq_key): # Step 1: Fetch transcript from FMP url = f"https://financialmodelingprep.com/api/v3/earning_call_transcript/{symbol}?quarter={quarter}&year={year}&apikey={api_key}" resp = requests.get(url) resp.raise_for_status() data = resp.json() if not data or "content" not in data[0]: return f"No transcript found for {symbol} {quarter} {year}" text = data[0]["content"] # Step 2: Clean and split clean_text = re.sub(r'\s+', ' ', text).strip() if "Question-and-Answer" in clean_text: prepared, qna = clean_text.split("Question-and-Answer", 1) else: prepared, qna = clean_text, "" # Step 3: Summarize with Groq prepared_summary = summarize_section(prepared, symbol, quarter, year) qna_summary = summarize_section(qna, symbol, quarter, year) # Step 4: Merge into final one-pager return f"""# {symbol} Earnings One-Pager — {quarter} {year}## Prepared Remarks{prepared_summary}## Q&A Highlights{qna_summary}""".strip()# Example runprint(summarize_earnings_call("NVDA", 2, 2024, API_KEY, GROQ_API_KEY)) With this setup, generating a summary becomes as simple as calling one function with a ticker and date. You can run it inside a notebook, integrate it into a research workflow, or even schedule it to trigger after each new earnings release. Free Stock Market API and Financial Statements API... Conclusion Earnings calls no longer need to feel overwhelming. With the Financial Modeling Prep API, you can instantly access any company’s transcript, and with Groq LLM, you can turn that raw text into a sharp, actionable summary in seconds. This pipeline saves hours of reading and ensures you never miss the key results, guidance, or risks hidden in lengthy remarks. Whether you track tech giants like NVIDIA or smaller growth stocks, the process is the same — fast, reliable, and powered by the flexibility of FMP’s data. Summarize Any Stock’s Earnings Call in Seconds Using FMP API was originally published in Coinmonks on Medium, where people are continuing the conversation by highlighting and responding to this story
Share
Medium2025/09/18 14:40