HeyGen Voice Turbo
HeyGen Voice Turbo is what fal calls the fast, low-cost tier of HeyGen Voice, HeyGen's in-house text-to-speech model. It takes the same request as the standard model: 24 library voices, cloning from a reference recording, 39 languages and an expressiveness setting, and returns 44.1 kHz WAV. We could not find a release date or announcement from HeyGen for the Turbo tier, and HeyGen's voice page does not mention it; fal's model listing dates both HeyGen voice endpoints 20 October 2026. On fal it costs $0.004 per thousand characters, under a seventh of the standard tier.
Anvisha Pai, Co-founder & CEO, Voyager
HeyGen
›What we asked for
Hi, I'm HeyGen Voice Turbo, the fast, low-cost tier of HeyGen's voice model. I can read in one of HeyGen's library voices or clone a voice from a short recording. Here is the same script every voice on this site reads, so you can compare us.
heygen/heygen-voice/turbo
voice: Cecily
returned 15.3 seconds of wav
At a glance
- Price
- $0.004 per thousand characters on fal; our four scripts cost under half a cent.
- Voices
- The same 24 library voices as HeyGen Voice; we used Cecily, as on the standard tier.
- Cloning
- The same reference_audio_url cloning as the standard tier.
- Languages
- 39, detected from the text unless set.
Other HeyGen Voice models: HeyGen Voice. Compare all 2.
Anvisha's take
We have not scored the four readings by ear; press play and judge the voice yourself. What we measured: Turbo read the four scripts for under half a cent in total, $0.0039, the cheapest run of any voice model on this site, a fifth of Kokoro's. Its readings were within three quarters of a second of the standard tier's on every script, and on two of them the same length to the hundredth. It was not quicker to return: its first request took 23 seconds, as the standard tier's did, and the rest four to six. It read with Cecily, the voice we gave HeyGen Voice.
HeyGen Voice Turbo real output: the same 4 scripts every model gets
Every voice model on this site gets the same 4 scripts, so you can compare like with like. These are the readings HeyGen Voice Turbo returned, one try each, nothing re-rolled or retouched. Generated on . The 4 readings took 4 to 23 seconds each and cost $0.0039 in total.
Pacing, warmth and whether the pauses land where a voice actor would put them.
›What we asked for
Meet the Ember mug. It keeps your coffee at exactly the temperature you choose, for up to ninety minutes, and it tells your phone when it's ready. Warm from the first sip to the last. Ember. Coffee, on your terms.
heygen/heygen-voice/turbo
voice: Cecily
returned 13.7 seconds of wav
Steady narration over a long paragraph, clean list rhythm and a natural close.
›What we asked for
A pour-over works in four steps. First, rinse the paper filter with hot water so it doesn't taste of paper. Second, add the grounds and pour just enough water to wet them, then wait thirty seconds while they bloom. Third, pour the rest of the water in slow circles. Fourth, wait about three minutes for it to drip through. That's it: a cup that tastes like the coffee, not the machine.
heygen/heygen-voice/turbo
voice: Cecily
returned 23.7 seconds of wav
Range: excitement, then a hushed aside, from the words alone with no tags.
›What we asked for
We did it! We actually did it! I can't believe it's finally over. Okay. Okay, deep breath. Let's not tell anyone until Monday, alright? Just... let me have this one quiet night.
heygen/heygen-voice/turbo
voice: Cecily
returned 11.6 seconds of wav
Reading numbers, times, currency, an email address and two hard names correctly.
›What we asked for
Your order ships on the 24th of September 2026 and arrives by 9:15 a.m. The total is $1,249.99, including VAT. Questions? Ask for Siobhan Nguyen or Ravi Parikh on 0800 555 0199, or email help@moda.app.
heygen/heygen-voice/turbo
voice: Cecily
returned 20.5 seconds of wav
How the cost under each picture was worked out: fal's HeyGen Voice Turbo rate of $0.004 per 1,000 characters (fal model page and pricing API, read 2026-10-22) for the 213 characters sent; fal does not return the charge.
Compare HeyGen Voice Turbo
HeyGen Voice Turbo pricing
| Where | Unit | Price | Source |
|---|---|---|---|
| fal | 1,000 characters | $0.004 | fal model page and pricing API, read |
Is HeyGen Voice Turbo free?
fal charges per character, with no free tier. HeyGen's own pages do not mention a Turbo tier, so we found no HeyGen price or free allowance for it.
- •fal: $0.004 per thousand characters.
- •HeyGen: no Turbo tier listed on its voice page.
fal model page, read
Where to use HeyGen Voice Turbo
- fal · $0.004 per thousand characters, library voices or a clone.
- HeyGen · The standard HeyGen Voice, in the app and API.
- Voyager · Runs inside Voyager, the agent for creative work, with your own fal key.
Voyager
Run HeyGen Voice Turbo inside Voyager
Voyager is an agent for creative work that runs every model in this reference, HeyGen Voice Turbo included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.
What we noticed running HeyGen Voice Turbo
- •13.67 seconds, the same length to the hundredth as the standard tier's reading, which is a different file. See the ad read reading.
- •11.60 seconds, again identical in length to the standard tier. See the emotional line reading.
- •The first request took 23.2 seconds to return; the next three took four to six. See the ad read reading.
HeyGen Voice Turbo limits and API parameters
| Limit | Value |
|---|---|
| Script length | 5,000 characters a request. fal API reference, read |
| Clone reference | Only the first three minutes of the recording are used. fal API reference, read |
| Output | 44.1 kHz WAV, with the duration in the response. fal API reference, read |
›Every setting, for developers
fal (heygen/heygen-voice/turbo)
fal API reference, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| text | string | The script, up to 5,000 characters Required. | |
| voice | enum | Jonah, Nadine, Tabitha, Soren, Elowen, Vincent, Jocelyn, Marielle, Corinne, Lucian, Kieran, Hugh, Noelle, Bram, Ewan, Iona, Cecily, Simon, Weston, Felicity, Gareth, Rory, Meredith, Sabrina Ignored when reference_audio_url is set. | Jonah |
| reference_audio_url | string | A recording of one speaker to clone Only the first three minutes are used. | |
| expressiveness_boost | number | 0 to 1 | 1 |
| language | enum | 39 language codes, from ar to zh Detected from the text when omitted. | |
| enable_safety_checker | boolean | true, false Only authorised callers may turn it off. | true |
What HeyGen Voice Turbo will not say
HeyGen's content moderation policy bars fraud, harassment, sexual content, child-safety violations, hate and misinformation, and requires explicit consent before making an avatar of a real person. It does not mention voices or voice cloning, so the consent rule for a cloned voice through fal's reference_audio_url is not spelled out there.
Alternatives to HeyGen Voice Turbo
Frequently asked questions
What is HeyGen Voice Turbo?
The fast, low-cost tier of HeyGen Voice on fal, with the same voices, cloning and 39 languages, at $0.004 per thousand characters.
How is Turbo different from HeyGen Voice?
Mainly price: $0.004 against $0.03 per thousand characters on fal, read on 22 October 2026. On our four scripts the readings were within a second of each other in length and it was not quicker to return.
When was HeyGen Voice Turbo released?
We could not verify a date from HeyGen. fal's model listing dates the endpoint 20 October 2026.
How this page is made
Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.
