Migrate from PlayHT to Inworld Realtime TTS After Shutdown

Why PlayHT Customers Need to Move Now

• Existing PlayHT API integrations are dead. The endpoints have been offline since mid-2025.
• Voice clones are gone. PlayHT deleted user voice data at the December 31, 2025 sunset. There is no recovery path through PlayHT.
• Your only option is to reclone from your original audio sources into a new provider.

Model Mapping: PlayHT to Realtime TTS

Migration Step 1: Reclone Your Voices

import requests
import base64

with open("original_voice_sample.wav", "rb") as f:
    audio_b64 = base64.b64encode(f.read()).decode()

# Step 1: Clone the voice
clone_response = requests.post(
    "https://api.inworld.ai/voices/v1/voices:clone",
    headers={"Authorization": "Basic <your-api-key>"},
    json={
        "displayName": "Customer Service Agent",
        "langCode": "EN_US",
        "voiceSamples": [
            {"audioData": audio_b64}
        ],
        "audioProcessingConfig": {"removeBackgroundNoise": True}
    }
)
voice_id = clone_response.json()["voice"]["voiceId"]

# Step 2: Use the cloned voice in TTS calls
tts_response = requests.post(
    "https://api.inworld.ai/tts/v1/voice",
    headers={"Authorization": "Basic <your-api-key>"},
    json={
        "text": "Hello, how can I help you today?",
        "voiceId": voice_id,
        "modelId": "inworld-tts-1.5-max",
        "audioConfig": {
            "audioEncoding": "MP3",
            "sampleRateHertz": 24000
        }
    }
)

with open("output.mp3", "wb") as f:
    f.write(base64.b64decode(tts_response.json()["audioContent"]))

• 5-15 seconds of clean original audio (samples >15s auto-trimmed).
• Formats: WAV, MP3, WEBM. Max 4MB per sample.
• 1,000 cloned voices per account (higher limits via enterprise sales).
• Use original human-recorded audio, not AI-generated PlayHT output. Generation-on-generation cloning compounds artifacts.

Migration Step 2: Swap the Synthesis API

# Before: PlayHT synthesis (legacy reference)
# response = playht.tts(text=text, voice="s3://voice-cloning-zero-shot/...", ...)

# After: Realtime TTS synthesis
import requests
import base64

response = requests.post(
    "https://api.inworld.ai/tts/v1/voice",
    headers={"Authorization": "Basic <your-api-key>"},
    json={
        "text": "Hello world",
        "voiceId": "Sarah",  # or your cloned voiceId
        "modelId": "inworld-tts-1.5-max",
        "audioConfig": {
            "audioEncoding": "MP3",
            "sampleRateHertz": 24000
        }
    }
)

audio_bytes = base64.b64decode(response.json()["audioContent"])
with open("output.mp3", "wb") as f:
    f.write(audio_bytes)

import requests
import base64
import json

with requests.post(
    "https://api.inworld.ai/tts/v1/voice:stream",
    headers={"Authorization": "Basic <your-api-key>"},
    json={
        "text": "Hello world",
        "voiceId": "Sarah",
        "modelId": "inworld-tts-1.5-mini",  # mini for lowest TTFB
        "audioConfig": {
            "audioEncoding": "PCM",
            "sampleRateHertz": 24000
        }
    },
    stream=True
) as r:
    for line in r.iter_lines():
        if not line:
            continue
        chunk_obj = json.loads(line)
        audio_bytes = base64.b64decode(
            chunk_obj["result"]["audioContent"]
        )
        # play / forward audio_bytes to client

Migration Step 3: Voice Library Mapping

import requests

response = requests.get(
    "https://api.inworld.ai/voices/v1/voices?languages=EN_US",
    headers={"Authorization": "Basic <your-api-key>"}
)

for voice in response.json()["voices"]:
    print(voice["voiceId"], voice["displayName"], voice.get("description"))

Migration Checklist

• [ ] Pull all original human-recorded voice samples used for PlayHT clones.
• [ ] Get an Inworld API key from the Portal.
• [ ] Reclone each voice via POST /voices/v1/voices:clone. Save the returned voiceId.
• [ ] Update synthesis calls: change endpoint, swap voice for voiceId, swap model for modelId, add audioConfig (audioEncoding + sampleRateHertz).
• [ ] Update streaming parsing: PlayHT used various streaming formats; Realtime TTS streaming is NDJSON with base64 audioContent per line.
• [ ] Decode base64 before writing audio. Both sync and streaming responses return base64.
• [ ] Test latency end-to-end. Realtime TTS Mini delivers ~120ms TTFB; Max delivers sub-200ms.
• [ ] If you used PlayHT for the full speech loop, consider migrating the LLM layer too. The Realtime Router is OpenAI SDK-compatible and routes to hundreds of models.

Why Realtime TTS After PlayHT

• Voice quality. #1 on Artificial Analysis Speech Arena, three of top five. PlayHT was a strong product; Realtime TTS pushes further on expressiveness and conversational naturalness.
• 15 production languages with native-speaker quality. PlayHT's multilingual coverage was uneven; Realtime TTS is engineered for production deployment in all 15.
• Full pipeline integration. Realtime TTS pairs with Realtime STT, the Realtime Router, and the Realtime API for end-to-end voice applications. PlayHT was TTS-only.

FAQ

What happened to PlayHT?

Can I migrate my PlayHT voice clones to a new provider?

Should I reclone using AI-generated PlayHT audio?

How does Realtime TTS compare to PlayHT on quality?

What is the easiest way to migrate code?