Project AURIONAI Use-Cases Research & Innovation
Microsoft AI
speech synthesis

SpeechT5

Unified speech and text encoder-decoder model; published checkpoints cover text-to-speech, voice conversion and recognition.

Microsoft AIMicrosoft AIUSA
Figure from the SpeechT5 paper: An illustration of the SpeechT5 framework, which treats spoken language processing tasks as a speech/text to speech/text format, including automatic speech reco.
Levelmodel
Classspeech synthesis
Parametersnot in the notes
Contextnot in the notes
Released14 Oct 2021
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

R&D Topics

Large-scale zero-shot text-to-speechproduced by

Identity

Developer
Microsoft AI
Family
not in the notes
Released
14 Oct 2021 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer shared encoder-decoder with modal pre and post nets
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text, audio
Output
audio, text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
MIT License sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2110.07205 https://arxiv.org/abs/2110.07205
  2. huggingface.co/microsoft/speecht5_tts https://huggingface.co/microsoft/speecht5_tts

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SpeechT5", https://aurion.semai.id/models/microsoft-speecht5/, records of October 2026.