Orpheus TTS
An incredibly lifelike speech synthesis model by Canopy Labs.
Deploy Orpheus TTS behind an API endpoint in seconds.
Example usage
Orpheus TTS must generate ~83 tokens/second for real-time streaming. This implementation supports streaming and, on an H100 MIG GPU, can produce seven concurrent real-time streams.
We'll be releasing a new version of this model soon with even better performance.
Input
1import asyncio
2import aiohttp
3import uuid
4import time
5import string
6
7BASETEN_HOST = "YOUR_PREDICT_URL"
8BASETEN_API_KEY = "YOUR_API_KEY"
9
10base_request_payload = {
11 "text": "Hey there! My name is Tara. How are you doing today?",
12 "max_tokens": 10000,
13 "voice": "tara"
14}
15
16async def stream_to_buffer(session, stream_label, payload):
17 """
18 Sends a streaming request and accumulates the response in a buffer.
19 """
20 unique_id = str(uuid.uuid4())
21 payload_with_id = payload.copy()
22 payload_with_id["request_id"] = unique_id
23
24 print(f"[{stream_label}] Starting request with request_id: {unique_id}")
25 start_time = time.time()
26
27 async with session.post(
28 BASETEN_HOST,
29 json=payload_with_id,
30 headers={"Authorization": f"Api-Key {BASETEN_API_KEY}"}
31 ) as resp:
32 if resp.status != 200:
33 print(f"[{stream_label}] Error: Received status code {resp.status}")
34 return b""
35 buffer = b""
36 chunk_count = 0
37 async for chunk in resp.content.iter_chunked(4096):
38 chunk_count += 1
39 now = time.time()
40 execution_time_ms = (now - start_time) * 1000
41 print(f"[{stream_label}] Received chunk {chunk_count} ({len(chunk)} bytes) after {execution_time_ms:.2f}ms")
42 buffer += chunk
43
44 total_time = time.time() - start_time
45 print(f"[{stream_label}] Completed receiving stream. Total size: {len(buffer)} bytes in {total_time:.2f}s")
46 return buffer
47
48async def main():
49 n = 1 # number of streams to run in parallel
50 stream_labels = [f"Stream{chr(65+i)}" for i in range(n)]
51
52 async with aiohttp.ClientSession() as session:
53 tasks = [
54 stream_to_buffer(session, label, base_request_payload)
55 for label in stream_labels
56 ]
57 results = await asyncio.gather(*tasks)
58
59 for label, buffer in zip(stream_labels, results):
60 filename = f"output_{label}.wav"
61 with open(filename, "wb") as f:
62 f.write(buffer)
63 print(f"Saved {filename}")
64
65if __name__ == '__main__':
66 asyncio.run(main())JSON output
1null
