Open ASR · AMI-Cleaned WER ↗English short-form; normalization unversioned
20.57% WERgoogle/gemma-4-E4B-it
googleDiscovered Oct 17, 2026
google/gemma-4-E4B-it
7.94B parameters · 140 languages · Encoder: Conformer · Decoder: Transformer
Measured performance
All leaderboards ↗Benchmark results
Word error rate · lower is better
Open ASR · Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned
14.16% WERgoogle/gemma-4-E4B-it
Open ASR · Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned
11.74% WERgoogle/gemma-4-E4B-it
Open ASR · LS Clean WER ↗English short-form; normalization unversioned
3.85% WERgoogle/gemma-4-E4B-it
Open ASR · LS Other WER ↗English short-form; normalization unversioned
9.97% WERgoogle/gemma-4-E4B-it
Open ASR · SPGISpeech WER ↗English short-form; normalization unversioned
5.49% WERgoogle/gemma-4-E4B-it
Open ASR · URGENT2024 WER ↗English short-form; normalization unversioned
26.38% WERgoogle/gemma-4-E4B-it
Open ASR · Voice Arena Monsoon WER ↗English short-form; normalization unversioned
6.19% WERgoogle/gemma-4-E4B-it
Open ASR · Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned
4.09% WERgoogle/gemma-4-E4B-it
Access & cost
0 quotesPrices across providers
No listed provider price
Model specifications
- Developer
- Modality
- Audio
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Not reported
- First discovered
- Oct 17, 2026
More from google
View all ↗googleReleased 24 days ago
Google: Gemini 3.8 Flash Lite TTS
Separate spoken text from delivery instructions, or script a two-voice dialogue with per-turn style overrides.
32.8K context
googleReleased 24 days ago
Google: Gemini 3.8 Flash TTS
Separates spoken text from delivery instructions; supports exactly two named speakers with ordered dialogue turns.
32.8K context
googleListed 27 days ago
Lyria 3.5
Lyria 3.5 is Google DeepMind's latest music generation model, and you can generate almost any type of music with it
No reported score
No reported score
googleListed Apr 24
Google: Gemini 3.1 Flash TTS Preview
Gemini 3.1 Flash TTS Preview is a text-to-speech model from Google, and a substantial generational step up from Gemini 2.5 Flash TTS. It takes text input and produces audio output...
32.8K contextNo reported score
No reported score
Price not listed