Model · Voice and speech

Sesame CSM

A free, downloadable speech model built to sound natural in back-and-forth conversation. Give it text, and optionally earlier audio for context, and it speaks the reply. Works best in English and needs technical setup.

Go to Sesame CSM’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
Apache 2.0, but downloads are gated: you must agree to share contact details.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Apache License 2.0 (Permissive (e.g. Apache 2.0, MIT))
Card also bans impersonating real people without explicit consent, misleading content and illegal use.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes
Follows from Apache 2.0; the card has no separate commercial clause but lists prohibited uses.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: Free to download (after agreeing to share contact details); free demo Space
Plans below.
How you use it: On your own computer, Through another service
DeepInfra listed as an inference provider; Colab and Kaggle notebooks. Sesame's own voice demo uses a fine-tuned version. Only the base model is released, not fine-tuned on a specific voice.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Sesame
No country stated on the model card.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
1B released 13 March 2025; built into Hugging Face Transformers from v4.52.1 (May 2025).
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A voice or speech, read my text aloud (main use)

text to audioaudio to audio

Designed for conversational speech (e.g. voice assistants) rather than reading documents; no closer task id exists.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Hugging Face

Other options for “A voice or speech, read my text aloud”

Adobe Firefly, Akool, Amazon Polly, Arcads, Async (formerly Podcastle), Azure AI Speech, Bark, CAMB.AI, Cartesia, Chatterbox, Clipchamp, Deepgram, DeeVid AI, Descript, Dia, Dubverse, Eleven v3, ElevenLabs, F5-TTS, fal, Filmora, Fish Audio, FlexClip, Fliki

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.