Pricing
$2.20 per minute of source media per target language, billed per second, rounded up.
Input Modalities
- Audio
- Video
Output Modalities
- Audio
Try this model
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AIHUBMIX_API_KEY"],
base_url="https://aihubmix.com/v1",
)
response = client.chat.completions.create(
model="dubbing_v2",
messages=[
{
"role": "user",
"content": "Hello, how are you?"
}
],
max_tokens=1024,
stream=False,
)
print(response.choices[0].message.content)Frequently asked questions
What is Dubbing v2?
How much does Dubbing v2 cost?
What modalities does Dubbing v2 support?
How do I call Dubbing v2 via API?
Who created Dubbing v2?
More models from ElevenLabs
See all ElevenLabs models →$0.50 per minute of source media per target language, billed per second, rounded up.
ElevenLabs Dubbing v1 translates and dubs audio or video into target languages while preserving the original speakers' voices. Call it via the ElevenLabs-compatible project API /v1/dubbing/project; billed by source media duration per target language.
$0.12 per minute of input audio, billed per second, rounded up to the next whole second.
ElevenLabs Voice Isolator: removes background noise, music and ambience to extract clean speech. Uses the native ElevenLabs endpoint POST /v1/audio-isolation; input audio must be at least 4.6 seconds; billed by input duration.
$0.12 per minute of input audio, billed per second, rounded up to the next whole second.
English-only voice changer (speech-to-speech): converts input audio into a target voice while keeping the original intonation and emotion. Uses the native ElevenLabs endpoint POST /v1/speech-to-speech/{voice_id}; official SDKs work by changing base_url. Billed by input duration.
$0.04 per 1K characters, billed by input characters (each letter or CJK character counts as one).
Ultra-fast English-only speech synthesis optimized for real-time use, with ~135ms latency and up to 30,000 characters per request. Call it through the OpenAI-compatible /v1/audio/speech endpoint with an ElevenLabs voice_id as voice; outputs mp3, opus, wav or pcm, with chunked streaming via stream_format=audio.
$0.04 per 1K characters, billed by input characters (each letter or CJK character counts as one).
ElevenLabs' fast, affordable speech synthesis model, with ~100ms latency across 32 languages and up to 40,000 characters per request, at half the per-character price. Built for voice agents, interactive apps and bulk conversion. Call it through the OpenAI-compatible /v1/audio/speech endpoint with an ElevenLabs voice_id as voice; outputs mp3, opus, wav or pcm, with chunked streaming via stream_format=audio.
$0.12 per minute of input audio, billed per second, rounded up to the next whole second.
ElevenLabs' recommended multilingual voice changer (speech-to-speech) covering 29 languages: converts input audio into a target voice while keeping the original intonation, pacing and emotion. Uses the native ElevenLabs endpoint POST /v1/speech-to-speech/{voice_id}; official SDKs work by changing base_url. Billed by input duration.