Skip to content
ESLog inStart free
A pulsar sweeping space with its two beams of lightA pulsar sweeping space with its two beams of light

The real-time voice modelEarly access

Pulsar 1 Low latency text to speech

Voice in about 100 milliseconds

median time to first audio, measured on the server

Real-time TTS for voice agents, assistants and phone lines. The same voices and the same quality as Voyager 1, speaking in about 100 ms.

  • 93–113 msmedian with 1 to 48 conversations at once
  • 800+ · 55+voices and languages: Voyager 1’s
  • μ-law · A-lawready for telephony

Same voice, new speed

Everything Voyager 1 does, at the speed of a conversation.

Many fast models trade quality for speed. Pulsar 1 doesn’t: it’s the same model as Voyager 1, built to respond. There’s no watered-down version of your voice.

What it shares with Voyager 1

800+library voices, the same ones you already know
55+languages, including native Castilian Spanish
Emotionsdirected with tags right in the text
Same qualitythe same voice, no downgrade for speed
[upbeat][hushed][belly laugh][unhappy]

What changes

3×Over three times sooner

to first audio than Voyager 1: Pulsar 1 starts speaking in about 100 ms.

WebSocketSentence by sentence

Streaming audio: the first chunk can arrive at the first comma.

LessLower cost per character

Pulsar 1 costs less than Voyager 1. We’ll publish the price right here at launch.

Latency under load

Real time at 1 conversation or 48.

Latency with a single request tells you little. We measured time to first audio with 1, 4, 8, 16, 24, 32 and 48 conversations at once, and the median never went above 113 ms.

93–113 msmedian time to first audio, from 1 to 48 conversations
95–125 msa typical agent sentence, delivered in full
Time to first audio by load (ms)

Measured on the server on 16 Oct 2026: median and 95th percentile of time to first audio at each load level. Network and your application are not included. The p95 is the time that 95 out of 100 responses come in under.

Demo

What a real-time conversation sounds like.

Real Pulsar 1 audio, in Spanish, across three sample calls: a dental clinic, a garage and an online store. Every reply shows its time to first audio, measured on the server; interrupt it and it stops to listen.

  • 1
    Answers without the silence

    Audio by sentence: the first chunk can arrive at the first comma, without waiting for the end of the text.

  • 2
    Stops when interrupted

    Send cancel with the turn’s context_id and it stops speaking right away.

  • 3
    Speaks with intent

    The same emotion tags as Voyager 1: [upbeat], [hushed]…

Appointments · Alba Dental ClinicVoice agent on Pulsar 1 · Spanish
Real Pulsar 1 audio, in Spanish
  1. Agent

    Hola, Lucía. Soy Clara, de la clínica dental Alba. ¿En qué te puedo ayudar?

    Hi, Lucía. This is Clara, from Alba Dental Clinic. How can I help you?

    144 ms · first audio
  2. Caller

    Hola, Clara. Tenía cita el jueves, pero me ha surgido un lío en el trabajo y no voy a poder ir.

    Hi, Clara. I had an appointment on Thursday, but something’s come up at work and I can’t make it.

  3. Agent

    [serene] Vale, entiendo lo que me cuentas. [comforting] Lo miramos ahora mismo y lo dejamos solucionado.

    Okay, I understand what you’re telling me. We’ll look at it right now and get it sorted.

    151 ms · first audio
  4. Caller

    ¿Podría ser el martes por la mañana?

    Could we do Tuesday morning?

  5. Agent

    [upbeat] Perfecto, ya tienes la cita confirmada para el martes a las diez.

    Perfect, your appointment is confirmed for Tuesday at ten.

    152 ms · first audio

Real Pulsar 1 audio, in Spanish, with the English translation underneath. On each reply, the time to first audio, measured on the server. Hit «Stop» while it speaks to see the cancel.

For developers

Real-time TTS over WebSocket.

Open a WebSocket, send text with speak and get audio back sentence by sentence. To cut it off, cancel. That’s it.

speak · flush · cancel

Three messages: speak, flush what’s pending, stop.

context_id

Each turn has its own: cut one off without closing the connection.

μ-law · A-law

Ready for telephony. PCM 16-bit and PCM float too.

24 kHz

Native, resampled to whatever rate your system uses.

Coming from another platform?

The Voicefinder REST API works with the most popular text to speech SDKs: change the base URL and the key, and you’re done.

How to migrate
import asyncio, json, os, websockets
URL = os.environ["PULSAR_WS_URL"] # pending: arrives with early access
async def main():
async with websockets.connect(URL) as ws: # authentication: pending
await ws.send(json.dumps({
"type": "speak", "context_id": "turn-1",
"model_id": "pulsar", # provisional
"voice_id": "VOICE_ID",
"text": "[upbeat] Hi! How can I help?",
}))
await ws.send(json.dumps({"type": "flush", "context_id": "turn-1"}))
async for chunk in ws:
player.write(chunk) # first audio in ~100 ms
asyncio.run(main())
The final URL, authentication and model_id arrive with early access.

Use cases

For everything that has to answer now.

Conversational agents

Your agent replies without the silence that gives a machine away, in your brand’s voices and languages.

Voice agents

Telephony and IVR

μ-law and A-law for the phone system: menus that answer instead of making people wait.

AI receptionist

In-app assistants

Spoken answers inside your product, in 55+ languages.

Games and NPCs

Characters that answer on the spot, with emotion: [hushed], [upbeat]…

Accessibility

Instant read-aloud for anyone who can’t, or would rather not, read the screen.

Models

Voyager 1 or Pulsar 1.

One model, two jobs: one produces, the other converses.

Voyager 1To produce
Pulsar 1To converse
Made for
Narration, advertising, dubbing and audiobooks
Voice agents, assistants, telephony, games and real-time apps
First audio
The whole file, in seconds
~100 ms
Delivery
MP3 or WAV file at 48 kHz
WebSocket streaming: PCM, μ-law or A-law
Voices and languages
800+ voices in 55+ languages
The same
Emotions
Tags in the text
The same
Price
On every plan
Lower cost per character
The Voyager Golden Record with its engraved pulsar mapThe pulsar map engraved on a metal plateThe pulsar map, simplified

The name

Why is it called Pulsar 1?

The Voyager 1 Golden Record carries a pulsar map: fourteen stars that tell anyone who finds it where the probe came from. Pulsars spin hundreds of times a second and sweep space with two beams of light, like a lighthouse.

They’re the most precise clocks in the universe. That’s why our fastest model is named after them.

Meet Voyager 1

FAQ

Low latency text to speech: your questions

Missing one? Ask us when you request early access.

What is Pulsar 1?

Pulsar 1 is Voicefinder’s low latency text to speech: the same model as Voyager 1, built to respond. It starts speaking in about 100 ms and streams audio over WebSocket, sentence by sentence, for voice agents, assistants, telephony, games and real-time apps.

How fast does it start speaking?

Median time to first audio is about 100 ms: between 93 and 113 ms with 1 to 48 concurrent conversations, measured on the server on 16 Oct 2026. A typical agent sentence arrives in full in 95-125 ms. Your network and your application come on top.

Does it sound worse than Voyager 1?

No. Pulsar 1 uses the same voices, the same 55+ languages, the same emotions and the same voice quality as Voyager 1. What changes is how the audio arrives: streamed sentence by sentence instead of as one complete file.

Does it work for phone calls?

Yes. Besides PCM 16-bit and PCM float, Pulsar 1 outputs μ-law and A-law, the telephony formats, at a native 24 kHz or resampled to whatever rate your phone system uses.

What happens if the user interrupts?

Your app sends cancel with that turn’s context_id and Pulsar 1 stops speaking. The connection stays open and the next turn starts with a new context_id.

How much does it cost?

Less per character than Voyager 1. We’ll publish the price on this page when Pulsar 1 launches; in the meantime, request early access and we’ll walk you through the terms.

How do I get started?

Pulsar 1 is in early access: request it and we’ll get in touch to set you up. Meanwhile, you can try the same voices with Voyager 1 in the studio or through the API.

Give your agent a voice in 100 ms.

Voyager 1’s voices at the speed of a conversation. Pulsar 1 is in early access.