Voices

// You supply play().
import { AssemblyAI } from "assemblyai";

const client = new AssemblyAI({ apiKey: process.env.ASSEMBLYAI_API_KEY });

const session = client.tts.session({ voiceId: "aai-sara" }); // the WebSocket API
const begin = await session.connect();
for await (const chunk of session.speak("Hi, thanks for calling.")) play(chunk);
await session.close();
console.log(begin.configuration.voice_id);

const response = await client.tts.synthesize({ text: "Hi, thanks for calling.", voice_id: "aai-sara" }); // the HTTP API
console.log(response.voiceId);

wss://tts.us.assemblyai.com/v1/ws?voice_id=aai-sara&sample_rate=24000&encoding=pcm_s16le

curl -sS --fail-with-body https://tts.us.assemblyai.com/v1/speech \
  -H "Authorization: $ASSEMBLYAI_API_KEY" \
  -d '{"text": "Hi, thanks for calling.", "voice_id": "aai-sara", "container": "wav"}' \
  -o sara.wav

// Fragment: selectedVoiceId comes from your voice picker; textLanguage is the
// language of the text you will send.
const session = client.tts.session({ voiceId: selectedVoiceId, language: textLanguage });
const response = await client.tts.synthesize({ text, voice_id: selectedVoiceId, language: textLanguage });

// Fragment: selectedVoiceId comes from your voice picker, and textLanguage is
// the language of the text you will send.
const params = new URLSearchParams({
  voice_id: selectedVoiceId,
  language: textLanguage,
  sample_rate: "24000",
  encoding: "pcm_s16le",
});