# Maya1 Review

> Maya1 review: Apache 2.0 expressive English TTS you can run on a single 16GB+ GPU; stands out for natural-language voice design and 20+ inline emotion tags.

![Maya1 logo](https://www.versusref.com/logos/maya1.png)

Apache 2.0 expressive English TTS you can run on a single 16GB+ GPU; stands out for natural-language voice design and 20+ inline emotion tags rather than audio-sample cloning, with real-time streaming via vLLM.

Among the 46 text-to-speech tools we track, Maya1 has the 43rd-widest language coverage.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about Maya1

Maya1 is a text-to-speech apis platform: apache 2.0 expressive English TTS you can run on a single 16GB+ GPU; stands out for natural-language voice design and 20+ inline emotion tags rather than audio-sample cloning, with real-time streaming via vLLM. This profile tracks every Maya1 fact we have verified, each linked to a primary source and dated.

Maya1 does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Maya1 quote, it is the fastest way for us to close that gap.

On capabilities, Maya1 covers streaming audio output, emotion / style controls, and self-host / on-prem option, and does not offer instant voice cloning. Each of those is verified against Maya1's own docs or dashboard, not marketing copy.

Placed against the 46 text-to-speech tools we track, Maya1's strongest showing is the 43rd-widest language coverage - a spread worth weighing against your own priorities.

In total we track 12 verified facts for Maya1 today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Maya1 fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Streaming audio output | ✓  Yes | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Instant voice cloning | ✗  No | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Languages supported | 1 languages | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Emotion / style controls | ✓  Yes | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Model weights license | Apache 2.0 | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | No official SDK | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Output formats | 24 kHz (SNAC codec) | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | 3B | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Hardware to self-host | Single GPU with 16GB+ VRAM (A100 | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Hosted API available | No | Jul 20 | [source](https://huggingface.co/maya-research/maya1) |
| Project maintenance status | Active | Jul 20 | [source](https://huggingface.co/maya-research/maya1/commits/main) |

Source: https://www.versusref.com/tts/tools/maya1/