Checking…Try it live
Timbreby Uploading

Read one sentence. Hear yourself say anything.

Clone your voice in seconds, then have it read any text in real time.

1Record your voice
Read this aloud in your normal voice

0:00 / 0:20
2Make it say anything
AI-generated

Record your voice first to unlock this step.

Hear the voices

Clone a voice from one sentence.

No training, no waiting. Your recording never trains a model.

Read one sentencein your normal voice
We check it’s youonly your own voice is cloned
Hear it say anythingstreamed as it’s generated

One voice, many uses

What Timbre does

Text to speech

Type it. Hear it as it’s made.

Every sentence checked

Optional: heard once before you hear it.

Speak, a second model listens, play if it matches, speak again if not. SpeakListenPlay No match? Again

    Clone from one sentence

    Read one line. That’s your voice.

    Ten languages, one voice

    Long text, steady voice

    First sentence to last, one person.

    Speech to text → Rhythm

    Timbre, as an API.

    One price. Streaming. OpenAI-compatible.

    $10per million UTF-8 bytes of text
    • 100,000 bytes free when you sign up
    • Pay only for text that produces audio
    • Voice cloning at no extra charge

    Concurrent requests scale with your total top-ups: 5 to start, 15 from $100, 50 from $1,000. Pricing

    from openai import OpenAI
    
    client = OpenAI(base_url="https://api.uploading.tech/v1", api_key=TIMBRE_API_KEY)
    with client.audio.speech.with_streaming_response.create(
        model="timbre-1", voice="VOICE_ID", input="Hello from Timbre.",
    ) as r:
        r.stream_to_file("hello.mp3")
    Already using the OpenAI SDK? Just change the base URL and key.Docs →

    FAQ

    How is Timbre priced?

    By the text that produces audio: $10 per million UTF-8 bytes of text. Failed requests are free.

    Can I clone my own voice for free?

    Yes. Read one sentence on this page to clone your voice right in your browser.

    Is my recording kept or used for training?

    No. Demo recordings stay in memory for 15 minutes, are never written to disk, and are never used for training.

    Whose voice can I clone?

    Your own, or that of someone who has agreed to how you’ll use it. Impersonating anyone to deceive is not allowed.

    Which languages does it speak?

    Chinese, English, Japanese, Korean, German, French, Spanish, Italian, Portuguese and Russian.

    Does it work with the OpenAI SDK?

    Yes. Set the SDK's base_url to https://api.uploading.tech/v1 and use a Timbre key.

    One sentence is all it takes.