Tasks and inputs
HeyGen Voice Turbo is listed for Audio, Text → Speech, Text-to-speech. It accepts text and produces audio. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Nov 17, 2026
HeyGen Voice Turbo is the low-latency version of HeyGen's TTS model for public voices and instant clones, at $4 per 1M characters.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Pricing conditions: Indicative: $4 per 1M characters via OpenRouter. Free variant until 2026-11-30 with no guarantees. Confirm on your account.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Latency is what makes a voice agent feel human or robotic. HeyGen Voice Turbo exists for that problem. It is the faster sibling of HeyGen's standard voice model, tuned to return audio sooner, and it gives up one thing to get there: professional voice clones are not supported.
You can still use public library voices and instant clones. Through OpenRouter, ten named voices are exposed, with output in mp3 or pcm.
Turbo is listed at $4 per 1M characters, a fraction of the standard model's rate. There is also a free variant, heygen-voice-1-turbo-free. It comes with clear caveats:
The free tier is fine for a prototype. Do not ship a product on it. Two weeks from now it ends, and even before then a busy afternoon can throttle you. Rates are indicative; confirm on your own account.
| Item | HeyGen Voice Turbo |
|---|---|
| API ID | heygen-voice-1-turbo |
| Free variant | heygen-voice-1-turbo-free (until 2026-11-30) |
| Voices | Public and instant clones only |
| IPA pronunciation | Paid tier only |
| Output formats (OpenRouter) | mp3, pcm |
| Indicative price | $4 per 1M characters |
If your brand relies on a professional clone, Turbo is off the table, so use the standard HeyGen Voice instead. The same applies when you need seed, pitch and break-tag controls for repeatable narration. Turbo is for conversation, not for audiobooks.
The release date is uncertain. We record 13 October 2026; a dated listing slug suggests 9 October.
Latency claims are only meaningful at your network edge. Stream twenty short replies, the length your agent actually speaks, and log time to first audio chunk for Turbo and for one competitor such as MiniMax Speech 2.8 Turbo. Run the test at your peak hour, on the paid tier. More candidates sit under text-to-speech models. Then listen to the clips back to back: a faster voice that mangles names will cost you more in user trust than it saves in milliseconds.
Compare the model on the work you need to complete.
HeyGen Voice Turbo is listed for Audio, Text → Speech, Text-to-speech. It accepts text and produces audio. Use the publisher’s input format and preprocessing for your chosen deployment.
Compare pronunciation, voice consistency and time to the first playable audio. Check the service’s billing unit for the actual script.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
zyphra
ZONOS3-Mini is Zyphra's open multilingual text-to-speech model: 800M MoE with ~100M active, zero-shot voice cloning in 43 languages and 80 ms first audio.
Alibaba
Qwen-Audio-3.1-TTS Plus is Alibaba's premium text-to-speech model for brand voices and dubbing, with fine-grained emotion tags and noise-robust voice cloning.
Mistral AI
Voxtral TTS 3 is Mistral's speech synthesis model for batch and streaming audio, with voice cloning, emotion tags and 35+ languages at $13 per 1M chars.
fish-audio
Fish Audio Drama 3 is an expressive 35B MoE text-to-speech model steered by bracketed directions, covering 83 languages, with downloadable weights.
heygen
HeyGen Voice is HeyGen's default text-to-speech model: about 39 languages, public and cloned voices, streaming with character timestamps.
Alibaba
Qwen-Audio-3.1-TTS Flash is Alibaba's streaming text-to-speech model for voice assistants, live chat and customer service, with system and cloned voices.