Speech & Audio Applications

​

Best Model for This

​

Quick Start

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({
  baseURL: "https://api.kymaapi.com/v1",
  apiKey: process.env.KYMA_API_KEY,
});

// 1. Speech-to-text
const transcript = await client.audio.transcriptions.create({
  model: "whisper-v3-turbo",
  file: fs.createReadStream("./sample.wav"),
});
console.log(transcript.text);

// 2. Text-to-speech (needs a funded balance)
const spoken = await client.audio.speech.create({
  model: "minimax-speech-turbo",
  voice: "female-shaonv", // or any voice from GET /v1/audio/voices
  input: transcript.text,
  response_format: "mp3",
});

fs.writeFileSync("./audio-summary.mp3", Buffer.from(await spoken.arrayBuffer()));

​

Tips

• Keep transcription and downstream text tasks separate so you can cache transcript text and retry cheaply.
• For subtitle or dubbing flows, keep each chunk short (3-10s) to reduce timeline drift.
• Use one stable translation model per session for consistent phrasing.
• Keep speech generation idempotent per segment so retries do not duplicate output.

​

Cost Estimate

​

Built with Kyma

• sonpiaz/haynoi is a dictation app that uses whisper-v3-turbo for transcription and a Gemini Flash model for cleanup.
• sonpiaz/watch-cli turns social videos into agent-ready assets with whisper-v3-turbo for transcript.
• sonpiaz/kyma-dub dubs videos end-to-end using whisper-v3-turbo for ASR and qwen-3.7-max as the default translation model.

​

Next Steps

• Streaming - stream partial output to clients
• Audio Transcriptions API - endpoint contract and formats