Gemini 3.5 Transcribe Live (Preview)

Model details

Model ID	`gemini-3.5-transcribe-live`
Best for	`实时语音转文字。边说边出字,适合听写与会议记录;仅控制台 Playground Live 可用。`
Provider	`google`
Context length	`32,000 tokens`
Capabilities	`realtime`
Access tier	`PAID`
Free trial	`No`
Endpoint	`Playground Live (console, invite only)`
Input	`AUDIO`
Output	`TEXT`
Price	`text in $4.20 / 1M · text out $25.20 / 1M · audio in $4.20 / 1M · audio out $25.20 / 1M`
Billed on	`TEXT_INPUT_TOKEN, TEXT_OUTPUT_TOKEN, AUDIO_INPUT_TOKEN, AUDIO_OUTPUT_TOKEN`

Examples

curl

curl https://api.mafdet.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-mafdet-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-transcribe-live",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Node.js

const res = await fetch("https://api.mafdet.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.MAFDET_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gemini-3.5-transcribe-live",
    messages: [{ role: "user", content: "Hello" }],
  }),
});
const data = await res.json();
console.log(data.choices[0].message.content);

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mafdet.ai/v1",
    api_key="sk-mafdet-xxxxxxxxxxxxxxxx",
)
resp = client.chat.completions.create(
    model="gemini-3.5-transcribe-live",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Common errors

See full errors & troubleshooting →