Phone-ready
Tuned for 8 kHz phone lines as well as clean app audio.
Speech to text · VoxVain Listen Preview
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.
“Target” figures are goals we have not measured yet, not results. Anything marked “Measured” is a number we took ourselves; your latency depends on network, region and text length.
Features
Tuned for 8 kHz phone lines as well as clean app audio.
Stream over WebSocket for agents, or post a file for transcripts.
Every word comes back with start and end times.
Callback numbers, order numbers and addresses come back as text you can use.
Example request
Every example uses plain HTTPS. Set VOXVAIN_API_KEY in your environment first.
curl https://api.voxvain.com/v1/stt \
-H "Authorization: Bearer $VOXVAIN_API_KEY" \
-F audio=@call.wav \
-F language=enimport os
import requests
with open("call.wav", "rb") as audio:
response = requests.post(
"https://api.voxvain.com/v1/stt",
headers={"Authorization": f"Bearer {os.environ['VOXVAIN_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.voxvain.com/v1/stt", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.VOXVAIN_API_KEY}` },
body: form,
});
console.log((await response.json()).text);Get a free API key in a minute, no card needed. Then follow the quickstart.