Indus-Labs/indus-pocket-tts
text-to-speech model by Indus-Labs
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Hindi and Hinglish text-to-speech that runs on a CPU: 51 ms to first audio on a single CPU thread, no GPU. --int8 loads compressed weights. It is about twice as fast and, in our tests, sounds the same. Measured on an AMD EPYC (Genoa) server with the install above. There are 20 Hindi and Hinglish call-centre lines; each stream is its own process with PyTorch pinned to one CPU thread. First audio is the time from submitting text, normalisation included, to receiving the first audio chunk, with the model already loaded and warmed up. To reproduce this on your own machine: python benchmark.py --int8 (add --streams 4 for parallel streams). Measured on an otherwise idle machine. When the same server was busy serving other traffic, the same build gave 57 ms p50 and 5.3× — so expect figures in that band under load. Run benchmark.py --int8 on your own hardware…
Read the full model card ↗ · Preview checked 2026-09-25T07:45:39.013Z
Inside the original model card — Document outline
- indus-pocket-tts
- Quick start
- From Python
- Performance
- Quality
- Samples
- How it was made
- Limitations
- Responsible use
- Licence and attribution
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: cc-by-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Indus-Labs/indus-pocket-tts is a text-to-speech model repository published by Indus-Labs on Hugging Face. The source reports the pocket-tts library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- pocket-tts
- Recent downloads (30 days)
- 0
- Cumulative likes
- 2
- Hugging Face trending score
- 1
- Reported safetensors parameters
- 109,502,146
- Architecture
- Not reported
- License
- cc-by-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-25T06:16:59.000Z
- Last modified
- 2026-09-25T06:25:21.000Z
Compatibility and lineage
Reported languages: hi, en
Reported base models: kyutai/pocket-tts
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-25T06:37:40.528Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.