# Google’s Gemini 3.5 Transcribe outperforms OpenAI’s GPT-Transcribe in multi-speaker accuracy

Digest AI · Generative AI & Models · published 2026-09-28T14:00:06Z

Canonical: https://digestai.news/story/googles-gemini-3-5-transcribe-outperforms-openais-gpt-transcribe-in-mu

## Summary

Google released **Gemini 3.5 Transcribe** on August 26, 2026, just four weeks after OpenAI’s **GPT-Transcribe**, creating a rare head-to-head comparison of two new transcription models. Both offer streaming and non-streaming versions, but Google’s model stands out for built-in **multi-speaker diarization** (up to three speakers) and **word-level timestamps**, eliminating the need for separate models. Google reports a **4.0% word error rate (WER)** for streaming and **2.6% for non-streaming**, while OpenAI’s GPT-Transcribe achieves **19.27% WER** (down from Whisper’s 40.37%) but lacks diarization natively, requiring additional calls to **gpt-4o-transcribe-diarize** for speaker attribution.

OpenAI’s model costs **$0.0045 per minute** for files and **$0.017 for streaming**, while Google’s pricing isn’t detailed in the article. The comparison highlights a clear trade-off: Google’s model excels in **multi-speaker accuracy and timestamps**, while OpenAI’s remains cheaper and simpler for single-speaker tasks or live captioning, where latency is critical.

## Key points

- Google’s Gemini 3.5 Transcribe cuts transcription time by 70% over its predecessor, Chirp 3, with built-in speaker labels and timestamps
- OpenAI’s GPT-Transcribe halves Whisper’s WER (from 40.37% to 19.27%) but requires extra models for speaker diarization and timestamps
- Google’s model supports **85+ languages** and integrates with other Gemini tools via function calling, while OpenAI’s focuses on cost efficiency

## Why it matters

For businesses needing accurate multi-speaker transcripts, Google’s model reduces pipeline complexity by combining diarization and timestamps into one call, while OpenAI’s remains the cheaper option for simpler use cases.

## Sources

1. [Gemini 3.5 Transcribe vs OpenAI’s GPT-Transcribe](https://kdnuggets.com/gemini-3-5-transcribe-vs-openais-gpt-transcribe) (KDnuggets, 2026-09-28)

Part of the developing story: [Google Gemini Expands Global Language Reach](https://digestai.news/thread/google-expands-ai-language-tools-to-300-languages-with-new-gemini-models) (2 stories)

## Cite

Digest AI, "Google’s Gemini 3.5 Transcribe outperforms OpenAI’s GPT-Transcribe in multi-speaker accuracy", 28 September 2026, https://digestai.news/story/googles-gemini-3-5-transcribe-outperforms-openais-gpt-transcribe-in-mu

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/googles-gemini-3-5-transcribe-outperforms-openais-gpt-transcribe-in-mu.json