Google: Chirp 3
google/chirp-3
Chirp 3 is Google's latest multilingual speech-to-text model. It offers enhanced transcription accuracy across 24 GA languages and 77+ preview languages, with support for automatic language detection, automatic punctuation, and a built-in denoiser for cleaner audio processing.
Input
$266.666666667
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
Not published
tokens
Transcription output · Token reference fields do not establish an output-unit price.
Model facts
Author
Tokenizer
Other
Modality
Audio -> Transcription
Created
May 5, 2026
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · AudioOutput · Transcription