Introducing Crosstalk 1 and Crosstalk 1 mini
14 July 2026
Crosstalk 1 and Crosstalk 1 mini are our new text-to-speech (TTS) models, optimized for mobile hardware. They stream speech faster than real time and start speaking almost instantly. They can also clone voices from short samples, emit word timings as they go, and have a compact download and memory footprint.
Crosstalk 1
A high-fidelity model for iOS.
- Platforms
- iOS
- Compatibility
- iPhone 15 up
- Download
- iOS: 534 MB
- Peak memory
- iOS: ~1.5 GB
Crosstalk 1 mini
Smaller and faster cross-platform model.
- Platforms
- iOS, Android
- Compatibility
- iPhone 12 Pro up, Fairphone 4 (2021) up
- Download
- iOS: 131 MB Android: 146 MB
- Peak memory
- iOS: ~2 GB Android: ~1 GB
Both are built on open-weight checkpoints that we've optimized and extended to give the best possible user experience.
Comparisons
Below we compare the Crosstalk models against other TTS models in their weight class. Models with cloning support were given the reference voice below to copy:
The reference voice clip.
TTFA (time to first audio) is how long you wait before the first sound of speech. A low TTFA makes generation feel instant.
RTF (real-time factor) is how long generation takes divided by the length of the audio it produces. Anything below 1 is faster than playback, and lower is always better – it widens the range of hardware that can keep up and lightens thermal load.
We tuned the Crosstalk models heavily for low TTFA and RTF to offer a near-instant, seamless speech generation experience.
Crosstalk 1
| Model | Download | Peak memory | Word timings | Cloning | Streams | ||
|---|---|---|---|---|---|---|---|
| Crosstalk 1 | 460 ms | 0.24 | 534 MB | 1.3 GB | live | yes | yes |
| NeuTTS Air 748M | 0.9 s | 1.30 | 839 MB | 1 GB | no | yes | yes |
| Qwen3-TTS 0.6B | 1.4 s | 0.72 | 2.0 GB | 4.5 GB | no | yes | yes |
| Marvis TTS 250M | 1.4 s | 0.68 | 940 MB | 1.9 GB | no | yes | yes |
Crosstalk 1 mini
| Model | Download | Peak memory | Word timings | Cloning | Streams | ||
|---|---|---|---|---|---|---|---|
| Crosstalk 1 mini | 85 ms | 0.19 | 146 MB | 870 MB | live | yes | yes |
| NeuTTS Nano | 610 ms | 0.56 | 506 MB | 1.3 GB | no | yes | yes |
| MOSS-TTS-Nano 100M | 9 s | 0.60 | 717 MB | 6.8 GB | no | yes | yes |
| Supertonic 3 99M | 3.7 s | 0.22 | 129 MB | 720 MB | no | no | no |
| Kokoro 82M | 2.1 s | 0.47 | 349 MB | 1.2 GB | no | no | yes |
| Piper 16M | 210 ms | 0.05 | 67 MB | 910 MB | no | no | yes |
On-device benchmarks
The comparisons above use one flagship phone per table; this section shows how the Crosstalk models perform across a wider range of iOS and Android devices.
Crosstalk 1
| Device | Year | Chip | ||
|---|---|---|---|---|
| iPhone 12 Pro | 2020 | A14 | 1500 ms | 1.1 |
| iPhone 15 | 2023 | A16 | 900 ms | 0.54 |
| iPhone 16 Pro | 2024 | A18 Pro | 700 ms | 0.53 |
| iPhone 17 Pro | 2025 | A19 Pro | 460 ms | 0.24 |
Crosstalk 1 mini
| Device | Year | Chip | ||
|---|---|---|---|---|
| iPhone 12 Pro | 2020 | A14 | 110 ms | 0.71 |
| iPhone 15 | 2023 | A16 | 70 ms | 0.50 |
| iPhone 16 Pro | 2024 | A18 Pro | 80 ms | 0.42 |
| iPhone 17 Pro | 2025 | A19 Pro | 50 ms | 0.26 |
| Fairphone 4 | 2021 | Snapdragon 750G | 350 ms | 0.78 |
| Pixel 8 | 2023 | Tensor G3 | 210 ms | 0.48 |
| Galaxy S25+ | 2025 | Snapdragon 8 Elite | 85 ms | 0.19 |
Details
Hardware acceleration
We optimized Crosstalk 1 for the Apple Neural Engine, which is why it runs best on recent iPhones. Crosstalk 1 mini has to run on Android too, so it uses the CPU and GPU on iOS, and the CPU alone on Android.
Word timings
Subtitles need word timings, and the usual way to get them is to run speech-to-text over the finished audio, or to force-align the script against it.
The Crosstalk models emit the timings themselves, so we get word-aligned subtitles for free. They're accurate enough to drive live, karaoke-style highlighting as the speech is generated, with no speech-to-text and no aligner in the pipeline.
Production-ready
Alongside driving RTF and TTFA down, we also cut the download size and peak memory so that the models fit into an app and run on as wide a range of hardware as possible.
In practice, Crosstalk 1 mini is small enough to ship inside an app bundle, so there's no separate model download before you can start generating speech. Crosstalk 1 is about a third smaller than the next comparable model, and both are far smaller and require less memory than the open-weight checkpoints they started from.
Crosstalk 1 mini ships in our flagship app later this month.