Gemini 3.5 Transcribe lists 85+ languages; Sume STT takes a hint
Google's changelog lists Gemini 3.5 Transcribe with 85+ languages and word timestamps. Sume STT returns words always and takes an optional language hint.
Google's Gemini API changelog lists Gemini 3.5 Transcribe (Aug 26) with 85+ languages and word timestamps, plus a Live variant for streaming. Sume STT 1.0 returns word timings on every job, accepts an optional BCP-47 language_code, and auto-detects when you omit it; it is limited to 10 minutes per job.
Side by side
Google facts are from its changelog; we did not find a price on that page, so none is quoted.
| Item | Gemini 3.5 Transcribe | Sume STT 1.0 |
|---|---|---|
| Languages | 85+ | Auto-detect; hint optional |
| Word timestamps | Yes | Always returned |
| Streaming variant | Gemini 3.5 Transcribe Live | None |
| Max audio per job | Not read | 600 seconds |
| Price | Not read | $0.01 per audio minute |
When the language hint helps
Auto-detect can fail on short clips or code-switched speech. If you know the language, pass it. If a recording mixes two, split it with timeline audio and transcribe each part with its own hint.
The word list feeds captions: Sume's caption endpoint accepts words, so a transcript can drive burned-in text without retyping.
What we cannot say
We did not verify accuracy for either product and publish no word-error numbers. Test ten of your own clips, including noisy ones, before choosing.
Sources
Related posts
More in Comparisons
- Gemini 3.8 Flash-Lite TTS for scratch VO vs a Sume TTS first cut
Flash-Lite TTS is Google's cheaper speech tier. If you want a scratch read before locking a script, here is how a first cut on Sume TTS 1.0 compares.
- Gemini 3.8 Flash TTS voice library vs Sume voice selectors
Gemini 3.8 Flash TTS lists 30 curated voices plus a larger extended library. Sume picks a voice by avatar or voice id. How the two selection models differ.
- Gemini API leads with Omni Flash, Veo 3.1 for specialists: and Sume?
Google's video docs recommend Gemini Omni Flash as the default and Veo 3.1 for specific needs. Sume has sume/auto or a pinned catalog id. How they line up.
- Grok Imagine, Qwen Image and Imagen 4 Fast all cost 2.5 cents on Sume
Grok Imagine, Qwen Image and Imagen 4 Fast each bill $0.025 per image on Sume. What separates them: ratios, n, edits. Choose the cheap row that fits your job.
Written by Sume