integrate-audio（集成音频）

Integrate Audio Generation

PREREQUISITE: Run +check-compatibility first. Run +fetch-api-reference to load the latest API reference before integrating. Requires +setup-api-key for API credentials. Requires +integrate-uploads for local audio/video files.

Help users add Runway audio generation to their server-side code.

Available Models

Text-to-Speech

Generate speech from text using the ElevenLabs multilingual model.

Node.js SDK

import RunwayML from '@runwayml/sdk';

const client = new RunwayML();

const task = await client.textToSpeech.create({
  model: 'eleven_multilingual_v2',
  text: 'Hello, welcome to our application!',
  voiceId: 'voice_id_here'  // See voice listing endpoint
}).waitForTaskOutput();

const audioUrl = task.output[0];

Python SDK

from runwayml import RunwayML

client = RunwayML()

task = client.text_to_speech.create(
    model='eleven_multilingual_v2',
    text='Hello, welcome to our application!',
    voice_id='voice_id_here'
).wait_for_task_output()

audio_url = task.output[0]

Sound Effects

Generate sound effects from text descriptions.

const task = await client.soundEffect.create({
  model: 'eleven_text_to_sound_v2',
  promptText: 'Thunder rolling across a stormy sky'
}).waitForTaskOutput();

task = client.sound_effect.create(
    model='eleven_text_to_sound_v2',
    prompt_text='Thunder rolling across a stormy sky'
).wait_for_task_output()

Voice Isolation

Extract voice from audio with background noise.

// If using a local file, upload first
const upload = await client.uploads.createEphemeral(
  fs.createReadStream('/path/to/noisy-audio.mp3')
);

const task = await client.voiceIsolation.create({
  model: 'eleven_voice_isolation',
  audio: upload.runwayUri
}).waitForTaskOutput();

Voice Dubbing

Dub audio/video into other languages.

const task = await client.voiceDubbing.create({
  model: 'eleven_voice_dubbing',
  audio: 'https://example.com/speech.mp3',
  targetLanguage: 'es'  // Spanish
}).waitForTaskOutput();

Speech-to-Speech

Convert one voice to another.

const task = await client.speechToSpeech.create({
  model: 'eleven_multilingual_sts_v2',
  audio: 'https://example.com/original-speech.mp3',
  voiceId: 'target_voice_id'
}).waitForTaskOutput();

Integration Pattern

Express.js — Text-to-Speech Endpoint

import RunwayML from '@runwayml/sdk';
import express from 'express';

const client = new RunwayML();
const app = express();
app.use(express.json());

app.post('/api/text-to-speech', async (req, res) => {
  try {
    const { text, voiceId } = req.body;

    const task = await client.textToSpeech.create({
      model: 'eleven_multilingual_v2',
      text,
      voiceId
    }).waitForTaskOutput();

    res.json({ audioUrl: task.output[0] });
  } catch (error) {
    console.error('TTS failed:', error);
    res.status(500).json({ error: error.message });
  }
});

FastAPI — Sound Effects

from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from runwayml import RunwayML

app = FastAPI()
client = RunwayML()

class SoundRequest(BaseModel):
    prompt: str

@app.post("/api/sound-effect")
async def generate_sound(req: SoundRequest):
    try:
        task = client.sound_effect.create(
            model='eleven_text_to_sound_v2',
            prompt_text=req.prompt
        ).wait_for_task_output()
        return {"audio_url": task.output[0]}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

Tips

• Output URLs expire in 24-48 hours. Download audio files to your own storage.
• For local audio files (voice isolation, dubbing, speech-to-speech), upload via +integrate-uploads first.
• Voice IDs can be listed via the voices endpoint — see +api-reference for details.
• Text-to-speech cost scales with text length: 1 credit per 50 characters.