SKILLoptionalHermes Optional Skills

Whisper

Name: Whisper
Author: Orchestra Research

Transcribe and translate speech in 99 languages

WhisperSpeech RecognitionASRMultimodalMultilingualOpenAISpeech-To-TextTranscription

Last registry verification2026-08-18v1.0.0Orchestra Research

Open original source ↗اقرأ بالعربية

Plain meaning

What does it add to Hermes?

Transcribe and translate speech in 99 languages

Whisper is a skill related to design and media. It adds tools to create, read, or modify media such as designs, images, audio, or video.

This plain-language explanation is based on the publisher description. The original text remains visible for verification.

Use it when

Use it when your goal in design and media is clear and you can limit it to the data and actions it actually needs.

Skip it when

Do not add it merely to experiment when Hermes already has a simpler path, or when you cannot review its source and permissions.

Who is it for?

Best for users who want a repeatable way of working inside Hermes.

Safe first test

Start with a disposable asset and create a copy instead of changing the original.

Original publisher description

Transcribe and translate speech in 99 languages

✓

Data source

This entry was indexed from Hermes Optional Skills. Our explanation interprets the type and domain without inventing a capability not present upstream.

Security review

The source is official or editorially reviewed, but you still need to review permissions and version compatibility.

Safe setup path

Inspect, install, then test.

01
Open the source
Match the publisher, license, and description to your need. Check the real update history.
02
Review permissions and secrets
Never paste a secret value into this site. Use environment-variable names and grant the smallest scope.
03
Copy setup only after review
The controls below copy text. They do not execute commands on your device.
04
Test with a non-sensitive task
Inspect the visible tools, then exclude write or delete tools you do not need.

Install command

Review the command, then copy it.

hermes skills install whisper

Hermes Belarabi does not execute this command. Installation happens on your device and remains subject to Hermes scanning and your review.

The full skill definition

Exactly what Hermes loads when this skill runs.

Reproduced from the official documentation. Read it before enabling the skill: this text becomes the agent's instructions.

Transcribe and translate speech in 99 languages.

Skill metadata

A lookup table. Do not read it all; find the row that applies to you.

Source	Optional — install with `hermes skills install official/mlops/whisper`
Path	`optional-skills/mlops/whisper`
Version	`1.0.0`
Author	Orchestra Research
License	MIT
Dependencies	`openai-whisper`, `transformers`, `torch`
Platforms	linux, macos
Tags	`Whisper`, `Speech Recognition`, `ASR`, `Multimodal`, `Multilingual`, `OpenAI`, `Speech-To-Text`, `Transcription`, `Translation`, `Audio Processing`

Reference: full SKILL.md

Explains the idea itself. Read it slowly; the later sections build on it.

OpenAI's multilingual speech recognition model.

When to use Whisper

Explains the idea itself. Read it slowly; the later sections build on it.

Use when:

Speech-to-text transcription (99 languages)
Podcast/video transcription
Meeting notes automation
Translation to English
Noisy audio transcription
Multilingual audio processing

Metrics:

72,900+ GitHub stars
99 languages supported
Trained on 680,000 hours of audio
MIT License

Use alternatives instead:

AssemblyAI: Managed API, speaker diarization
Deepgram: Real-time streaming ASR
Google Speech-to-Text: Cloud-based

Quick start

Ordered, practical steps. Run one and confirm it worked before moving on.

Installation

Shell7 lines

# Requires Python 3.8-3.11
pip install -U openai-whisper

# Requires ffmpeg
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
# Windows: choco install ffmpeg

Basic transcription

Python14 lines



# Load model
model = whisper.load_model("base")

# Transcribe
result = model.transcribe("audio.mp3")

# Print text
print(result["text"])

# Access segments
for segment in result["segments"]:
    print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}")

Model sizes

A lookup table. Do not read it all; find the row that applies to you.

Python5 lines

# Available models
models = ["tiny", "base", "small", "medium", "large", "turbo"]

# Load specific model
model = whisper.load_model("turbo")  # Fastest, good quality

Model	Parameters	English-only	Multilingual	Speed	VRAM
tiny	39M	✓	✓	~32x	~1 GB
base	74M	✓	✓	~16x	~1 GB
small	244M	✓	✓	~6x	~2 GB
medium	769M	✓	✓	~2x	~5 GB
large	1550M	✗	✓	1x	~10 GB
turbo	809M	✗	✓	~8x	~6 GB

Recommendation: Use turbo for best speed/quality, base for prototyping

Transcription options

Explains the idea itself. Read it slowly; the later sections build on it.

Language specification

Python7 lines

# Auto-detect language
result = model.transcribe("audio.mp3")

# Specify language (faster)
result = model.transcribe("audio.mp3", language="en")

# Supported: en, es, fr, de, it, pt, ru, ja, ko, zh, and 89 more

Task selection

Python6 lines

# Transcription (default)
result = model.transcribe("audio.mp3", task="transcribe")

# Translation to English
result = model.transcribe("spanish.mp3", task="translate")
# Input: Spanish audio → Output: English text

Initial prompt

Python10 lines

# Improve accuracy with context
result = model.transcribe(
    "audio.mp3",
    initial_prompt="This is a technical podcast about machine learning and AI."
)

# Helps with:
# - Technical terms
# - Proper nouns
# - Domain-specific vocabulary

Timestamps

Python6 lines

# Word-level timestamps
result = model.transcribe("audio.mp3", word_timestamps=True)

for segment in result["segments"]:
    for word in segment["words"]:
        print(f"{word['word']} ({word['start']:.2f}s - {word['end']:.2f}s)")

Temperature fallback

Python5 lines

# Retry with different temperatures if confidence low
result = model.transcribe(
    "audio.mp3",
    temperature=(0.0, 0.2, 0.4, 0.6, 0.8, 1.0)
)

Command line usage

Explains the idea itself. Read it slowly; the later sections build on it.

Shell17 lines

# Basic transcription
whisper audio.mp3

# Specify model
whisper audio.mp3 --model turbo

# Output formats
whisper audio.mp3 --output_format txt     # Plain text
whisper audio.mp3 --output_format srt     # Subtitles
whisper audio.mp3 --output_format vtt     # WebVTT
whisper audio.mp3 --output_format json    # JSON with timestamps

# Language
whisper audio.mp3 --language Spanish

# Translation
whisper spanish.mp3 --task translate

Batch processing

Explains the idea itself. Read it slowly; the later sections build on it.

Python12 lines



audio_files = ["file1.mp3", "file2.mp3", "file3.mp3"]

for audio_file in audio_files:
    print(f"Transcribing {audio_file}...")
    result = model.transcribe(audio_file)

    # Save to file
    output_file = audio_file.replace(".mp3", ".txt")
    with open(output_file, "w") as f:
        f.write(result["text"])

Real-time transcription

Explains the idea itself. Read it slowly; the later sections build on it.

Python12 lines

# For streaming audio, use faster-whisper
# pip install faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel("base", device="cuda", compute_type="float16")

# Transcribe with streaming
segments, info = model.transcribe("audio.mp3", beam_size=5)

for segment in segments:
    print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")

GPU acceleration

Explains the idea itself. Read it slowly; the later sections build on it.

Python12 lines



# Automatically uses GPU if available
model = whisper.load_model("turbo")

# Force CPU
model = whisper.load_model("turbo", device="cpu")

# Force GPU
model = whisper.load_model("turbo", device="cuda")

# 10-20× faster on GPU

Integration with other tools

Explains the idea itself. Read it slowly; the later sections build on it.

Subtitle generation

Shell4 lines

# Generate SRT subtitles
whisper video.mp4 --output_format srt --language English

# Output: video.srt

With LangChain

Python10 lines

from langchain.document_loaders import WhisperTranscriptionLoader

loader = WhisperTranscriptionLoader(file_path="audio.mp3")
docs = loader.load()

# Use transcription in RAG
from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings

vectorstore = Chroma.from_documents(docs, OpenAIEmbeddings())

Extract audio from video

Shell5 lines

# Use ffmpeg to extract audio
ffmpeg -i video.mp4 -vn -acodec pcm_s16le audio.wav

# Then transcribe
whisper audio.wav

Best practices

Explains the idea itself. Read it slowly; the later sections build on it.

Use turbo model - Best speed/quality for English
Specify language - Faster than auto-detect
Add initial prompt - Improves technical terms
Use GPU - 10-20× faster
Batch process - More efficient
Convert to WAV - Better compatibility
Split long audio - <30 min chunks
Check language support - Quality varies by language
Use faster-whisper - 4× faster than openai-whisper
Monitor VRAM - Scale model size to hardware

Performance

A lookup table. Do not read it all; find the row that applies to you.

Model	Real-time factor (CPU)	Real-time factor (GPU)
tiny	~0.32	~0.01
base	~0.16	~0.01
turbo	~0.08	~0.01
large	~1.0	~0.05

Real-time factor: 0.1 = 10× faster than real-time

Language support

Explains the idea itself. Read it slowly; the later sections build on it.

Top-supported languages:

English (en)
Spanish (es)
French (fr)
German (de)
Italian (it)
Portuguese (pt)
Russian (ru)
Japanese (ja)
Korean (ko)
Chinese (zh)

Full list: 99 languages total

Limitations

Explains the idea itself. Read it slowly; the later sections build on it.

Hallucinations - May repeat or invent text
Long-form accuracy - Degrades on >30 min audio
Speaker identification - No diarization
Accents - Quality varies
Background noise - Can affect accuracy
Real-time latency - Not suitable for live captioning

Resources

Explains the idea itself. Read it slowly; the later sections build on it.

GitHub: https://github.com/openai/whisper ⭐ 72,900+
Paper: https://arxiv.org/abs/2212.04356
Model Card: https://github.com/openai/whisper/blob/main/model-card.md
Colab: Available in repo
License: MIT