Chirp 3 is the latest generation of Google's multilingual ASR-specific generative models on the Speech-to-Text v2 API, generally available since October 2025 in the US and EU multi-regions.
- Input
- audio
- Output
- text
- Price
- $0.016/min
Price in context
Where the price sits among 11 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Audio
| Languages | 29 GA + 82 Preview locales (111 total) across StreamingRecognize, Recognize and BatchRecognize; diarization covers 14 of them |
|---|---|
| Audio limits |
|
| Speaker diarization | Yes |
| Streaming transcription | Yes |
| Timestamps | Yes |
Model
| Modalities | audio → text |
|---|
- 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)import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.audio.transcriptions.create({
model: "chirp-3",
file: fs.createReadStream("meeting.mp3"),
});
console.log(resp.text);curl https://synthorai.io/v1/audio/transcriptions \
-H "Authorization: Bearer sk-syn-..." \
-F model="chirp-3" \
-F file=@meeting.mp3package main
import (
"context"
"fmt"
"os"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
f, _ := os.Open("meeting.mp3")
resp, _ := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
Model: "chirp-3",
File: f,
})
fmt.Println(resp.Text)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.audio.transcriptions.*;
import java.nio.file.Paths;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
Transcription resp = client.audio().transcriptions().create(
TranscriptionCreateParams.builder()
.model("chirp-3")
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());About Chirp 3
- The official documentation highlights enhanced accuracy and speed beyond previous Chirp models plus two new capabilities: speaker diarization and automatic language detection.
- It publishes more than a hundred locales across generally available and preview tiers, generates automatic punctuation and capitalization, and accepts speech adaptation with up to 1,000 phrase hints, though Google recommends using as few entries as possible so non-adaptation terms do not degrade.
- Streaming, synchronous, and batch recognition are all supported, and diarization is available in batch recognition across fourteen languages.
- New controls include a custom prompt in preview for steering transcript formatting, a denoiser flag that Google warns cannot remove background human voices, and endpointing sensitivity at standard, short, or supershort.
- The upgrade is not purely additive, and the gaps are worth checking before switching: Chirp 3 documents utterance-level rather than word-level timestamps, does not document speech translation or a profanity filter, and caps batch audio at one hour, or twenty minutes when timestamps are enabled, against Chirp 2's eight.
- On Synthorai, Chirp 3 is reachable via the same OpenAI-compatible transcription interface as every other speech model.
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; transcribes more than 100 languages and variants; 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 29 GA + 82 Preview locales (111 total) across StreamingRecognize, Recognize and BatchRecognize; diarization covers 14 of them. 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
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.