Earningswhispers logo

Earningswhispers

Community
gauss314
earningswhispers

Earnings transcripts completos via API publica de EarningsWhispers. Sin anti-bot, sin auth. 33,500+ stocks globales trackeados. Test ok en mas de 60 tickers, AAPL, MSFT, GGAL, SHEL, TM, VALE etc

Overview

Publishergauss314
Repositoryskills
Skill nameearningswhispers
Stars
250
Forks
35
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by gauss314 on GitHub. Read the source before you install it.

Installation

Install the Earningswhispers AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/gauss314/skills/tree/main/skills/earningswhispers
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/gauss314/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/earningswhispers .claude/skills/earningswhispers
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Earningswhispers in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Earningswhispers on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Earningswhispers is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

EarningsWhispers — Earnings Transcripts API (Cobertura Global)

Skill para extraer earnings transcripts completos de EarningsWhispers via su API publica.

A diferencia de Seeking Alpha, este sitio tiene una API publica abierta sin autenticacion, sin anti-bot, y sin rate limiting agresivo. Los transcripts incluyen texto completo de las earnings calls con participantes, prepared remarks y Q&A.


API Endpoint

GET https://www.earningswhispers.com/api/conferencecalls?t={TICKER}
ParametroTipoDescripcion
tstring (requerido)Ticker del simbolo bursatil (AAPL, MSFT, GGAL, SHEL...)
ccidintID interno de conference call (opcional, no habilita historicos)

Response: Array JSON. Si el ticker existe, el array contiene 1 objeto con el ultimo transcript. Si no existe, devuelve array vacio.

Respuesta tipica (~50 KB para GGAL, ~90 KB para AAPL):
[{
  "ccid": 132,
  "ticker": "GGAL",
  "company": "Grupo Financiero Galicia S.A.",
  "ccDate": "2026-05-14T11:00:00",
  "ccYear": 2026,
  "ccQtr": 1,
  "speakers": "JSON string con array de speakers",
  "speakerMap": "JSON string con mapping de nombres y cargos",
  "summary": null,
  "aiSummary": null,
  "status": ""
}]

Cobertura Real

EarningsWhispers trackea ~33,500+ stocks globales en su plataforma. De esos, una proporcion significativa tiene earnings transcripts completos disponibles via la API.

Que empresas tienen transcripts?

Cualquier empresa publica que realice earnings conference calls puede tener transcript. En la practica:

  • Large caps: Cobertura casi total (AAPL, MSFT, JPM, SHEL, TM...)
  • Mid caps: Alta cobertura (la mayoria tiene transcripts)
  • Small caps: Cobertura parcial (depende de si hacen calls publicos)
  • ADRs: Cobertura alta para ADRs argentinos, brasilenos, mexicanos...
  • ETFs, fondos, bonds: Sin cobertura (no hacen earnings calls)

Como saber si un ticker tiene transcript?

Solo hay que probar la API:

bash
# Si devuelve datos, tiene transcript
curl "https://www.earningswhispers.com/api/conferencecalls?t=AAPL"

# Si devuelve [] (array vacio), no tiene transcript
curl "https://www.earningswhispers.com/api/conferencecalls?t=XXXX"

Ejemplos por region al 05-30-2026

US — Cobertura masiva (cualquier empresa publica US con earnings calls):

TickerEmpresaTranscript
AAPLApple Inc.✅ Q2 2026
MSFTMicrosoft Corp.✅ Q3 2026
GOOGAlphabet Inc.✅ Q1 2026
AMZNAmazon.com, Inc.✅ Q1 2026
METAMeta Platforms, Inc.✅ Q1 2026
NVDANVIDIA Corp.✅ Q1 2027
TSLATesla, Inc.✅ Q1 2026
JPMJPMorgan Chase & Co.✅
VVisa Inc.✅
WMTWalmart Inc.✅
DISWalt Disney Co.✅
NKENike Inc.✅
XOMExxon Mobil Corp.✅
UNHUnitedHealth Group✅
PFEPfizer, Inc.✅
DALDelta Air Lines✅
COINCoinbase Global✅

Europa:

TickerEmpresaTranscript
SHELShell plc✅
BPBP p.l.c.✅
TTETotalEnergies SE✅
HSBCHSBC Holdings✅
BBVABBVA✅

Asia:

TickerEmpresaTranscript
TMToyota Motor Corp.✅
HMCHonda Motor Co.✅
BABAAlibaba Group✅
JDJD.com, Inc.✅
TCEHYTencent Holdings✅
INFYInfosys Technologies✅

LatAm:

TickerEmpresaTranscript
ITUBItau Unibanco✅
BBDBanco Bradesco✅
VALEVale S.A.✅
AMXAmerica Movil✅
FMXFomento Economico Mexicano✅
SBSCia de Saneamento✅
WMMVYWalmart Mexico✅

Argentina:

TickerEmpresaTranscript
GGALGrupo Financiero Galicia✅ Q1 2026
YPFYPF S.A.✅ Q1 2026
TGSTransportadora de Gas✅ Q1 2026
PAMPampa Energia✅ Q4 2025
BMABanco Macro✅

Sobre los tickers que no funcionan

Algunos tickers pueden no tener transcript por estas razones:

MotivoEjemplos
No hacen earnings callsETFs (SPY, QQQ, ARKK), bonds
Ticker incorrectoGOOGL -> GOOG, WALMEX -> WMMVY
No cubiertos en la baseAlgunos small caps
Empresa quebrada/fusionadaSBNY, FRC

Notas sobre Tickers

  • GOOGL no funciona, usar GOOG (Alphabet)
  • WALMEX no funciona, usar WMMVY (Walmart Mexico)
  • SNE (antiguo Sony) ya no existe, SONY tampoco esta cubierto
  • Tickers que no existen en la base devuelven [] (array vacio)

Instalacion

bash
python -c "from curl_cffi import requests; print('OK')"

Dependencia: curl_cffi (ya disponible en el entorno).


Scripts

ScriptDescripcion
ew_client.pyCliente completo con CLI integrado
ew_cli.pyCLI wrapper

Uso Rapido

CLI

bash
# Cualquier ticker global
python ew_cli.py get AAPL
python ew_cli.py get SHEL --json
python ew_cli.py batch MSFT,GOOG,AMZN --json
python ew_cli.py info GGAL

# Lista de tickers de ejemplo
python ew_cli.py list

Desde Python

python
from ew_client import EarningsWhispersClient

client = EarningsWhispersClient()

# Transcript de cualquier empresa global
tr = client.get_transcript("AAPL")
print(tr.company)                    # "Apple, Inc."
print(tr.prepared_remarks[:500])

# Como dict (para JSON)
data = tr.to_dict()

# Batch
results = client.get_transcripts_batch(["MSFT", "GOOG", "AMZN"])

Campos Clave del Transcript

python
tr = client.get_transcript("NVDA")
tr.company          # "NVIDIA Corp."
tr.date             # "2026-05-20T16:30:00"
tr.quarter_label    # "Q1"
tr.year             # 2027 (fiscal year)
tr.prepared_remarks # Texto de la presentacion
tr.qa_section       # Preguntas y respuestas
tr.summary          # Resumen ejecutivo (puede ser None)
tr.ai_summary       # Resumen AI (puede ser None)

Cache

  • Cache local en .cache/transcript_{TICKER}.json
  • Expiracion: 24 horas
  • Forzar refresh: --no-cache o force_refresh=True
  • El cache NUNCA almacena cookies ni credenciales

Limitaciones

  1. Solo ultimo transcript: La API devuelve solo el mas reciente. No hay historico completo.
  2. Sin search endpoint: No hay forma de descubrir tickers disponibles programaticamente.
  3. Sin autenticacion Google/Facebook: La pagina web requiere login; la API no.
  4. Cobertura no exhaustiva: ~33,500 stocks trackeados, pero no todos tienen transcripts (depende de si hacen earnings calls publicos).
  5. Sin datos historicos: El parametro ccid no habilita acceso a transcripts anteriores.

Referencias

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Earningswhispers AI skill do?

Earnings transcripts completos via API publica de EarningsWhispers. Sin anti-bot, sin auth. 33,500+ stocks globales trackeados. Test ok en mas de 60 tickers, AAPL, MSFT, GGAL, SHEL, TM, VALE etc

Why use Earningswhispers on TypingMind?

Because you install it once and use it with any model. Earningswhispers is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Earningswhispers in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gauss314/skills/tree/main/skills/earningswhispers. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Earningswhispers?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Earningswhispers?

As many as you like. As long as a model supports skills, you can use Earningswhispers with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Earningswhispers AI skill free?

Yes. It is published on GitHub by gauss314 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇