Skip to content
Sesame CSM

Open source alternatives to Sesame CSM

200 open source apps like Sesame CSM, closest match first.

Top picks

  1. C

    ChatTTS

    Launch

    A generative speech model for daily dialogue.

    Open source

  2. M

    Minimind O

    Launch

    MiniMind-O is an open-source omni model with about 0.1 billion parameters, built from scratch in PyTorch. A single set of weights takes text, speech and images as input and produces text and streaming speech as output. It is the third model

    Open source

  3. S

    Speechgpt

    Launch

    SpeechGPT is a web application that enables you to converse with ChatGPT. You can utilize this app to improve your language speaking skills or simply have fun chatting with ChatGPT.

    Open source

  4. T

    TTS-WebUI

    Launch

    A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos,

    Open source

  5. M

    MioTTS-Inference

    Launch

    Inference server for MioTTS, a lightweight and fast LLM-based TTS model.

    Open source

  6. P

    Parlant

    Launch

    A conversational AI server that manages agent behavior through context-aware guidelines, keeping responses consistent, auditable, and aligned at scale.

    Open source

More like Sesame CSM

7
L

LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction…

Launch
8
C

ComfyUI-VoxCPM

ComfyUI node for highly expressive speech and realistic zero-shot voice cloning

Launch
9
V

VibeVoice-ComfyUI

A comprehensive ComfyUI integration

Launch
10
D

Dia

A TTS model capable of generating ultra-realistic dialogue in one pass

Launch
11
A

Aiavatarkit

Building AI-based conversational avatars lightning fast

Launch
12
L

LLMVoX

Autoregressive Streaming Text-to-Speech Model for Any LLM

Launch
13
S

Sayna

Sayna is a unified Voice Layer for AI Agents

Launch
14
C

ComfyUI-VibeVoice

ComfyUI custom node for the VibeVoice TTS

Launch
15
C

Chatterbox-TTS-Server

Self-host the powerful Chatterbox TTS model

Launch
16
C

CleanS2S

High-quality and streaming Speech-to-Speech interactive agent in a single file

Launch
17
M

MOSS-TTS

An open-source model family for long-form speech, dialogue synthesis

Launch
18
A

AivisSpeech

AI Voice Imitation System - Text to Speech Software

Launch
19
V

Voice Studio

A multi-model local AI Voice Generator (TTS) studio

Launch
20
V

Voice Chat AI

🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI…

Launch
21
S

Speech-AI-Forge

Speech-AI-Forge is a project developed around TTS generation model

Launch
22
D

Dia-TTS-Server

Self-host the powerful Dia TTS model

Launch
23
C

CosyVoice

Multi-lingual large voice generation model, providing inference

Launch
24
S

Step-Audio-EditX

A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model

Launch
25
V

VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation

Launch
26
N

Nari Qwen3 TTS

Ultrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second

Launch
27
A

AudioCraft

A single-stop code base for generative audio needs, by Meta

Launch
28
C

Chat JS

Production-ready AI chat. Start here and make it your own. Formerly Sparka AI

Launch
29
L

LLaSA_training

LLaSA: Scaling Train-time and Inference-time Compute

Launch
30
C

ComfyUI-VoxCPM2

VoxCPM2 TTS for ComfyUI

Launch
31
M

MGM-Omni

Scaling Omni LLMs to Personalized Long-Horizon Speech

Launch
32
S

StreamSpeech

StreamSpeech is an “All in One” seamless model for offline

Launch
33
O

OpenLive

Opensource, on-device voice + vision layer for AI agents

Launch
34
A

ASR-Studio

Multi-provider ASR web studio (Qwen, Doubao, Gemini, NIM, OpenAI-compatible &…

Launch
35
S

Speech To Speech

Build voice agents with open-source models

Launch
36
C

CrispASR

C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe

Launch
37
M

mbailey/voice-mcp

Voice interaction: speech-to-text

Get
38
A

Audio.cpp-webui

audio.cpp with a full-task WebUI - pure C++ audio-model inference engine…

Launch
39
C

Chaplin

A real-time silent speech recognition tool

Launch
40
X

Xiaogpt

Play ChatGPT and other LLM with Xiaomi AI Speaker

Launch
41
P

Portable-Local-Studio

Portable local AI studio for Windows, Linux, and macOS

Launch
42
V

Voxtream

VoXtream is a Full-Stream Zero-shot TTS model

Launch
43
C

Chatterbox TTS API

Local, OpenAI-compatible text-to-speech

Launch
44
B

Baibot

A Matrix bot for using different capabilities

Launch
45
V

Vox Box

A text-to-speech and speech-to-text server compatible

Launch
46
S

Stream-Omni

Stream-Omni is a GPT-4o-like language-vision-speech chatbot

Launch
47
U

Unsaged

Open source chat kit engineered for seamless interaction with AI models

Launch
48
A

Audio Webui

A webui for different audio related Neural Networks

Launch
49
A

Airunner

Offline inference engine for art, real-time voice conversations

Launch
50
C

ChatGPT-OpenAI-Smart-Speaker

This AI Smart Speaker uses speech recognition, TTS (text-to-speech), and STT

Launch

About Sesame CSM

S

Sesame CSM

Conversational speech generation

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.

Price
Free
Made by
sesame
Category
AI
Website
huggingface.co/spaces/sesame/csm-1b