Phone-ready
Tuned for 8 kHz phone lines as well as clean app audio.
Speech to text · VoxVane Listen Preview
Transcripts you can act on.
Accurate speech to text for phone calls and app audio. Upload a file, or stream live audio and get words back as they are spoken.
Example≈150 msstreaming partial results
Example≈6%word error rate on phone audio
TodayEnglishUS and UK today
Example figures until we publish measured benchmarks.
Features
What you get.
Live or batch
Stream over WebSocket for agents, or post a file for transcripts.
Word timings
Every word comes back with start and end times.
Numbers and names
Callback numbers, order numbers and addresses come back as text you can use.
Example request
Try it from your terminal.
Every example uses plain HTTPS. Set VOXVANE_API_KEY in your environment first.
Speech to textPreview API
curl https://api.voxvane.com/v1/stt \
-H "Authorization: Bearer $VOXVANE_API_KEY" \
-F audio=@call.wav \
-F language=enimport os
import requests
with open("call.wav", "rb") as audio:
response = requests.post(
"https://api.voxvane.com/v1/stt",
headers={"Authorization": f"Bearer {os.environ['VOXVANE_API_KEY']}"},
files={"audio": audio},
data={"language": "en"},
timeout=60,
)
print(response.json()["text"])import { readFile } from "node:fs/promises";
const form = new FormData();
form.append("audio", new Blob([await readFile("call.wav")]), "call.wav");
form.append("language", "en");
const response = await fetch("https://api.voxvane.com/v1/stt", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.VOXVANE_API_KEY}` },
body: form,
});
console.log((await response.json()).text);Start building with VoxVane.
The API is in private preview. Read the quickstart, then ask for a key.