Open in the interactive docs · markdown for agents: https://neuraldeep.tech/docs/tts.md

Speech synthesis · TTS API

With the same key — speech synthesis under /v1/audio/speech: text → audio (WAV 24 kHz). The Qwen3-TTS model on our GPUs. Available on all plans, a separate bucket — the limit is counted in characters of input text. The request format is OpenAI-compatible and works synchronously: send text → get an audio file right away.

8 voices: vivian, serena, ono_anna, sohee (female) · dylan, ryan, aiden, uncle_fu (male) — multilingual. 10 languages: Russian, English, German, French, Spanish, Italian, Chinese, Japanese, Korean, Portuguese (+Auto). Emotion and style are set as free text in instructions ("cheerfully", "a calm announcer"). Voice list: GET /v1/audio/voices. The quota remainder comes with every response in the X-Quota-Day-Remaining and X-Quota-Month-Remaining headers. Exhaustion: 429 with a quota_exceeded body and Retry-After.

🇷🇺 Russian — with stress marks. With language=Russian the synthesis uses a separate model, ESpeech (F5 + RUAccent) — it places stress correctly and resolves homographs by context (zamók "a lock" → zámok "a castle"), where ordinary TTS gets it wrong. Other languages run on Qwen3-TTS. Which engine synthesized is shown in the response header X-TTS-Engine (espeech/qwen). To set stress manually — put + before the stressed vowel («zam+ok»); if + is already in the text, the auto-accentizer doesn't intervene.

# synthesis (voice serena, Russian) → file
curl -s https://api.neuraldeep.tech/v1/audio/speech \
  -H "Authorization: Bearer $YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"input":"Hello! This is speech synthesis on our servers.","voice":"serena","language":"Russian"}' \
  -o speech.wav

# with emotion (via instructions)
curl -s https://api.neuraldeep.tech/v1/audio/speech \
  -H "Authorization: Bearer $YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"input":"Congratulations on the release!","voice":"vivian","language":"Russian","instructions":"cheerfully, with enthusiasm"}' \
  -o happy.wav

# manual stress via "+" (zam+ok = padlock) — RUAccent doesn't intervene if "+" is already present
curl -s https://api.neuraldeep.tech/v1/audio/speech \
  -H "Authorization: Bearer $YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"input":"On povesil ambarnyy zam+ok.","voice":"serena","language":"Russian"}' \
  -o stress.wav

# voice list
curl https://api.neuraldeep.tech/v1/audio/voices -H "Authorization: Bearer $YOUR_KEY"

import httpx

r = httpx.post(
    "https://api.neuraldeep.tech/v1/audio/speech",
    headers={"Authorization": "Bearer $YOUR_KEY"},
    json={"input": "Text to synthesize.", "voice": "dylan", "language": "Russian"},
)
open("speech.wav", "wb").write(r.content)

The limit is counted in text characters (len(input)), not requests. Voice cloning from a sample is not available yet.

Input limits and errors.

input is required, up to 5,000 characters per call. Empty text gives 400, longer text 413. Split long text by sentences and join the audio.
An unknown voice gives 400 with the voice list. OpenAI voices (alloy, nova and others) are mapped to close ones of ours, so the OpenAI SDK works as is: client.audio.speech.create(model="tts-1", voice="alloy", input=...). The voice actually used comes back in the X-TTS-Voice header.
Output: WAV, 24 kHz, mono, 16-bit. The response has to fit into 120 seconds.
A voice cloning attempt: 403. A synthesis failure returns the quota and an error with the engine status.

Speech synthesis · TTS API

Reference sections (markdown for agents)