Streaming TTS

curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/mpeg' \
  --header 'Authorization: Bearer $RIME_API_KEY' \
  --header 'Content-Type: application/json' \
  --output output.mp3 \
  --data '{
  "text": "Streaming audio from Rime, as it is generated.",
  "modelId": "coda",
  "speaker": "astra",
  "lang": "en"
}'

import os, requests

with requests.post(
    "https://users.rime.ai/v1/rime-tts",
    headers={
        "Authorization": f"Bearer {os.environ['RIME_API_KEY']}",
        "Content-Type": "application/json",
        "Accept": "audio/mpeg",
    },
    json={
        "text": "Streaming audio from Rime, as it is generated.",
        "modelId": "coda",
        "speaker": "astra",
        "lang": "en",
    },
    stream=True,
) as response:
    response.raise_for_status()
    for chunk in response.iter_content(chunk_size=4096):
        ...  # feed chunk to your player, telephony stream, or file

import asyncio, base64, json, os
import websockets

async def main():
    url = "wss://users-ws.rime.ai/ws3?speaker=astra&modelId=coda&audioFormat=mp3"
    headers = {"Authorization": f"Bearer {os.environ['RIME_API_KEY']}"}

    async with websockets.connect(url, additional_headers=headers) as ws:
        await ws.send(json.dumps({"text": "Hello from Rime over WebSockets."}))
        await ws.send(json.dumps({"operation": "eos"}))  # synthesize and close

        async for message in ws:
            event = json.loads(message)
            if event["type"] == "chunk":
                audio_bytes = base64.b64decode(event["data"])
                ...  # play or forward the audio
            elif event["type"] == "timestamps":
                print(event["word_timestamps"]["words"])
            elif event["type"] == "done":
                print("synthesis complete")

asyncio.run(main())