Live market

voxtral-mini-tts-3-0

Mistral: Voxtral TTS 3

Nobody is selling this model right now. The prices below are the published rate, not an offer — a request would find no supply. They are kept visible so the rate can be watched and compared.

Quoted share of list: 80%
Quoted output price: 10.40 /1M chars USDT
Sellers online: 0
Calls / min: 0

Calling this model

POST /audio/speech — the same request OpenAI's SDKs already send. Point the base URL at asale and change nothing else.

billed per character of input

INPUT

The text to read aloud.

Which voice reads it.

Encoding of the returned audio.

Playback speed multiplier; 1 is normal.

Minimum charge per request: 0.000013 USDT

Output

Run it to see the answer here.

Or call it from your own code

curl https://gw.asale.ai/v1/audio/speech \
  -H "Authorization: Bearer $ASALE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "voxtral-mini-tts-3-0",
    "input": "Hello from the asale media market.",
    "voice": "voice_3150",
    "response_format": "mp3"
  }' \
  --output speech.mp3

import os, requests

r = requests.post(
    "https://gw.asale.ai/v1/audio/speech",
    headers={"Authorization": f"Bearer {os.environ['ASALE_API_KEY']}"},
    json={
      "model": "voxtral-mini-tts-3-0",
      "input": "Hello from the asale media market.",
      "voice": "voice_3150",
      "response_format": "mp3"
    },
)
r.raise_for_status()
open("speech.mp3", "wb").write(r.content)

const r = await fetch("https://gw.asale.ai/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ASALE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "voxtral-mini-tts-3-0",
    "input": "Hello from the asale media market.",
    "voice": "voice_3150",
    "response_format": "mp3"
  }),
});
if (!r.ok) throw new Error(await r.text());
await Bun.write("speech.mp3", await r.blob());

Request fields

Field	Type	Accepts	Meaning
modelrequired	string	—	Which model serves the request.
inputrequired	text	—	The text to read aloud.
voicerequired	enum	voice_3150 · voice_478 · voice_447 · voice_485 · en_paul_sad · en_paul_neutral	Which voice reads it.
response_format	enum	mp3 · pcm	Encoding of the returned audio.
speed	number	0.25 … 4	Playback speed multiplier; 1 is normal.

Response

The audio itself, as bytes — not JSON. Write it straight to a file.

Priced item	List	Market	Of list price
Output	13.00 /1M chars	10.40 /1M chars	80%

Channel quality

What has been measured about the supply behind this price. Readings, not promises — and aggregate, because which seller failed is nobody's business but theirs and ours.

Online lanes: 0
Verified lanes: —; Proved they serve this model
First byte (p50): —
Success rate: —; No turns settled in the window
Sellable capacity: —; Tokens offered right now

Latency and verification are measured over the last day; the success rate comes from settled traffic. See the status page

Price trend

Currently selling at 80% of the vendor's list price. More sellers online push it down; more buyers push it back up to list.

Of list price: 80%
Sellers online: 0
Calls / min: 0

Market depth

No live asks for this model.

MIvoxtral-mini-tts-3-0

voxtral-mini-tts-3-0