Minh/speech transcription tutorial

[minh-hoque]

Summary

This pull-request adds a new end-to-end tutorial, examples/Speech_transcription_methods.ipynb, that compares four different ways to convert speech to text with OpenAI tools:

1. Audio /transcriptions endpoint (single request)
2. Audio /transcriptions with streaming
3. Speech Realtime API (web-socket)
4. Agents SDK with the new speech_to_text tool

The notebook walks through the trade-offs, provides helper functions, and benchmarks each approach on several sample files.
To support the tutorial we also add:

• Sample audio clips (examples/data/sample_audio_files/…)
• Explanatory diagrams (Mermaid source in examples/mermaid/… and rendered PNGs in examples/imgs/…)
• Updates to .gitignore (ignore large/temporary audio)

Together these assets give cookbook readers a practical, runnable reference for choosing the right transcription workflow.

Motivation

High-quality speech transcription is a common requirement for chatbots, call-analysis, meeting notes, and real-time assistants. OpenAI now offers multiple APIs and SDK features for this, but the differences (latency, code patterns, streaming vs. batch, etc.) are not obvious to newcomers.

This tutorial:

• Shows concrete, runnable examples for every current method
• Highlights pros / cons and performance considerations
• Provides reusable helper code and diagrams to speed up adoption

Adding this content will make the Cookbook a good guide for developers integrating speech capabilities.

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml (and, optionally, in authors.yaml) so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.

[danial-openai]

Some tiny nits but otherwise LGTM. Thanks for writing this up!

[minh-hoque]

Some tiny nits but otherwise LGTM. Thanks for writing this up!

Thank you for the review @danial-openai! Changes have been pushed.