Speech (TTS / STT)

Text-to-speech (TTS)

POST /v1/audio/speech

Converts text into speech and returns an audio binary stream.

Request parameters

Parameter	Type	Required	Description
model	string	✅	TTS model, e.g. tts-1 (standard), tts-1-hd (HD)
input	string	✅	Text to synthesize (up to 4096 characters)
voice	string	✅	Voice, see options below
response_format	string	—	Audio format: mp3 (default), opus, aac, flac, wav, pcm
speed	number	—	Speed, range 0.25–4.0 (default 1.0)

Available voices

Voice	Style
alloy	Neutral, balanced
echo	Rich, steady
fable	Warm, narrative
onyx	Deep, authoritative
nova	Lively, friendly
shimmer	Soft, clear

Example

cURL

curl https://api.idreame.ai/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -d '{
    "model": "tts-1",
    "input": "Welcome to iDreame Cloud, your one-stop entry to AI.",
    "voice": "nova"
  }' \
  --output welcome.mp3

Python

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    base_url="https://api.idreame.ai/v1",
    api_key="sk-xxxxxxxx",
)

response = client.audio.speech.create(
    model="tts-1",
    voice="nova",
    input="Welcome to iDreame Cloud, your one-stop entry to AI.",
)

Path("welcome.mp3").write_bytes(response.content)

---

Speech-to-text (STT)

POST /v1/audio/transcriptions

Converts an audio file into text (transcription). Upload the file with multipart/form-data.

Request parameters

Parameter	Type	Required	Description
file	file	✅	Audio file (mp3, mp4, mpeg, mpga, m4a, wav, webm; up to 25MB)
model	string	✅	Recognition model, e.g. whisper-1
language	string	—	Language code (e.g. zh, en); auto-detected if omitted
prompt	string	—	Optional prompt to guide style or correct proper nouns
response_format	string	—	Output format: json (default), text, srt, vtt, verbose_json
temperature	number	—	Sampling temperature 0–1

Example

cURL

curl https://api.idreame.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -F "file=@recording.mp3" \
  -F "model=whisper-1" \
  -F "language=en"

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.idreame.ai/v1",
    api_key="sk-xxxxxxxx",
)

with open("recording.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="en",
    )

print(transcript.text)

Response example

{
  "text": "Welcome to iDreame Cloud."
}

Subtitle output

Set response_format=srt to output an SRT subtitle file directly:

curl https://api.idreame.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -F "file=@video_audio.mp3" \
  -F "model=whisper-1" \
  -F "response_format=srt"

Output:

1
00:00:00,000 --> 00:00:02,500
Welcome to iDreame Cloud.

2
00:00:02,800 --> 00:00:05,200
Your one-stop entry to AI.