🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

Chirp 3 Released 2025-10-13

Google transcription
Price$0.016/min

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Official model id is chirp_3; private preview 2025-04-11, GA 2025-10-13 per Speech-to-Text release notes; billed per audio.

Use Chirp 3 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/audio/transcriptions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.audio.transcriptions.create(
    model="chirp-3",
    file=open("meeting.mp3", "rb"),
    language="en",
)
print(resp.text)

About Chirp 3

Speaker diarization and automatic language detection
Transcribes more than 100 languages and variants
Speech adaptation with up to 1,000 phrase hints

Chirp 3 is the latest generation of Google's multilingual ASR-specific generative models on the Speech-to-Text v2 API.

  • The official documentation highlights enhanced accuracy and speed beyond previous Chirp models plus two new capabilities: speaker diarization and automatic language detection.
  • It transcribes more than 100 languages and variants, generates automatic punctuation and capitalization, and accepts speech adaptation with up to 1,000 phrase hints, with streaming, synchronous, and batch recognition all supported.
  • On Synthorai, Chirp 3 is reachable via the same OpenAI-compatible transcription interface as every other speech model.

Specs & limits

Modalitiesaudio → text
Featuresstreaming · batch · diarization
Audio limitsAuto-detected audio decoding; sync Recognize <1 min, BatchRecognize 1 min-1 hr (<=20 min with word timestamps), StreamingRecognize for real-time; speaker diarization (BatchRecognize only, 14 languages); language-agnostic transcription; 25 GA + 75+ preview languages
NotableOfficial model id is chirp_3; private preview 2025-04-11, GA 2025-10-13 per Speech-to-Text release notes; billed per audio.

per Google official docs ↗

FAQ

Is the Chirp 3 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try Chirp 3 against your real workload before adding a payment method.

What is Chirp 3 best at?

Speaker diarization and automatic language detection, plus transcribes more than 100 languages and variants and speech adaptation with up to 1,000 phrase hints. See the About section for the full picture from the vendor's own release notes.

How much does Chirp 3 cost?

Chirp 3 costs $0.016 per minute of audio transcribed on Synthorai: pay-as-you-go, no platform markup, no subscription.

Which languages does Chirp 3 support?

Chirp 3 supports speaker diarization (BatchRecognize only, 14 languages). On Synthorai you call it through POST /v1/audio/transcriptions, the OpenAI transcription API shape.

How do I get access to Chirp 3?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="chirp-3", and you're done. One API key covers every model on the gateway.

Related models

Get your free API key Compare your cost →