HeyGen Voice Turbo API
The Turbo tier of HeyGen Voice: the same 24 preset voices at a much lower price.
$0.01/min on Varosity credits ($0.0036/min with your own key).
no fal.ai account needed · provider's list price; credits round each call up to the cent · failed renders never billed
Best for
- very cheap
- 24 preset voices
- 39 languages, detected from the text
Trade-offs
- WAV output only (large files)
- no streaming
How to get the best result
High-volume narration and drafts, with the same preset voices as heygen-voice at a much lower price. Pick instead: heygen-voice for the standard tier; deepgram-aura-2 or cartesia-sonic-3.6 when you need streaming.
Prompting
- Plain text, up to 5,000 characters. Use punctuation to control pacing, since speed is not forwarded.
- The language is detected from the text; set providerOptions.language when a short line could be misread.
Settings on Varosity
- voiceId is a preset name from list_voices (default Jonah). Anything else is refused and not charged.
- REST providerOptions: language (ISO code such as en, es, ja) and expressivenessBoost (0-1, default 1).
- Output is 44.1 kHz WAV, about 5 MB a minute; format and speed are not forwarded.
- The 1 cent minimum per call means very short lines cost more than the per-character rate suggests.
Avoid
- Passing another provider's voice id or a recording URL: both are refused.
Example prompt
Your order has shipped and should arrive on Thursday. Reply to this message if anything looks wrong.
From fal.ai, checked against what Varosity sends.
Call it from your code
One Varosity key works for every model.
curl -X POST https://varosity.ai/api/v1/tts \
-H "Authorization: Bearer $VAROSITY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"text": "Welcome to the launch. Here's what's new this week.",
"voiceModel": "heygen-voice-turbo"
}'Or ask your agent
Connect Claude, Cursor, or any MCP client to https://varosity.ai/api/mcp with your key, then say:
"Use Varosity with heygen-voice-turbo to read this script aloud: …"Agent setup guide
Alternatives to HeyGen Voice Turbo
- Kokoro (fal)open-weight (MIT) · runs on CPU$0.02/min
- Cartesia Sonic 3~90ms TTFA · 42 languages$0.06/min
- Cartesia Sonic 3.6~90ms TTFA · 42 languages$0.06/min
- Chatterbox (fal)open-weight (MIT) · expressive + emotion control$0.04/min
- Deepgram Aura 2ultra-low latency · natural prosody$0.03/min
- ElevenLabs Multilingual v229 languages · emotion control$0.08/min