Find a model

Browse the full catalog →

Voxtral 4B TTS

Text-to-speech model from Mistral. One API key reaches this provider and every other model in the catalog.

Price$0.00211/request
Providers 1 provider, one key

No card required. Start with 1 million free tokens.

Overview

About Voxtral 4B TTS

Voxtral 4B TTS is a text-to-speech model published by Mistral. Through TrustedRouter it runs on 1 provider, with options in the US and EU, from $0.00211/request. One provider offers zero data retention, and Tinfoil also runs it in a confidential enclave.

Model ID
mistralai/voxtral-4b-tts-2603
Publisher
Mistral
Input limit
4096 characters
Price
$0.00211/request
Formats
wav
Voices
neutral_female, neutral_male, casual_female, casual_male, cheerful_female, ar_male, de_female, de_male, es_female, es_male, fr_female, fr_male, hi_female, hi_male, it_female, it_male, nl_female, nl_male, pt_female, pt_male
Modes
speech
Billing
Credits
Quickstart

Set it up with your agent

Paste this into Claude Code, Cursor or any coding agent.

Use Voxtral 4B TTS through TrustedRouter in this project.

1. Read https://trustedrouter.com/llms.txt
2. Point the OpenAI-compatible client at
   https://api.trustedrouter.com/v1 and read the key from
   TRUSTEDROUTER_API_KEY.
3. Set the model to mistralai/voxtral-4b-tts-2603.
4. Run the tests, then show me the diff before committing.
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key=os.environ["TRUSTEDROUTER_API_KEY"],
)
with client.audio.speech.with_streaming_response.create(
    model="mistralai/voxtral-4b-tts-2603",
    input="Hello from TrustedRouter.",
    voice="neutral_female",
    response_format="wav",
) as response:
    response.stream_to_file("speech.wav")
curl https://api.trustedrouter.com/v1/audio/speech \
  -H "Authorization: Bearer $TRUSTEDROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/voxtral-4b-tts-2603", "input": "Hello from TrustedRouter.", "voice": "neutral_female"}' \
  --output speech.wav
Your agent will need an API key.
1 provider

Providers

Audio requests use the listed model and provider. These routes do not silently switch models or providers. Open a row for retention, location and weight format, or see how we check privacy claims and the live speed leaderboard.

Voxtral 4B TTS providers and prices per 1M tokens
Provider Price Output Details
Tinfoil logo Tinfoil ConfidentialZero retention $0.00211/request Included

Retention

Confidential compute with end-to-end encryption and zero data retention.

Tracked as a confidential inference provider with attested provider compute and no prompt/output logging claims.

Provider policy source

Location

Operator country: US

Headquarters / registered office: Not verified.

Inference: Inference location not verified; no country-specific residency commitment.

No inference-location declaration has been verified for this provider.

Region pinning through TR: No verified provider-specific location pin documented here.

Full location evidence

Weight format

Unknown

Price and speed

Input $0.00211/request · Cached input Not applicable · Output Included

TTFT: insufficient data

Speed: insufficient data

Tinfoil provider page

Usage

How to use Mistral: Voxtral 4B TTS

Text-to-speech, billed per request over an attested connection.

Input
POST /v1/audio/speech with model, input (text), voice, and response_format.
Output
Raw audio bytes. Errors are JSON. See supported response_formats.

Example input

{"model":"mistralai/voxtral-4b-tts-2603","input":"Hello!","voice":"neutral_female","response_format":"wav"}

Example output

Binary audio, not a JSON envelope.
FAQ

Questions

What model ID should I use for Voxtral 4B TTS?

Use mistralai/voxtral-4b-tts-2603 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Do you log my prompts or outputs?

No. Prompt and output content are intentionally excluded from the control plane and metadata systems. Optional content export requires explicit destination-level configuration.

Which providers serve Voxtral 4B TTS?

TrustedRouter currently lists Tinfoil for Voxtral 4B TTS. Provider availability and routing eligibility can change as catalog and health data update.

How much does Voxtral 4B TTS cost through TrustedRouter?

The current Credits price is $0.00211/request. Output is included; these are audio prices, not text-token prices.

How do I require zero data retention for Voxtral 4B TTS?

Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.

Compare

Voxtral 4B TTS vs other models

Start building with Voxtral 4B TTS.

No card required. Start with 1 million free tokens.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

New to TrustedRouter?

By continuing you agree to the terms of service and privacy policy.