# Multi-speaker Support

CSM (Conversational Speech Model) is a 1B-parameter speech generation model developed by Sesame, capable of generating RVQ audio encoding from text and audio inputs.

CSM (Conversational Speech Model) is a 1-billion-parameter speech generation model developed by Sesame, capable of generating RVQ audio encoding from text and audio inputs.

CSM is a 1B-parameter speech generation model developed by Sesame, capable of generating RVQ audio codes from text and audio inputs, supporting context-aware speech generation.

CSM (Conversational Speech Model) is a 1-billion-parameter speech generation model developed by Sesame, capable of generating RVQ audio encoding from text and audio inputs.

A PyTorch-based text-to-speech model supporting Chinese speech synthesis, developed and released by SesameAILabs.

Experimental speech synthesis model based on Amis and Taroko languages, trained using the ithuan dataset

Brazilian Portuguese text-to-speech model based on F5-TTS, supporting emotion tags and speaker feature control

Parler-TTS Mini v1.1 is a lightweight text-to-speech model trained on 45,000 hours of audio data, capable of generating high-quality, natural-sounding speech with controllable features through simple text prompts.

A Turkish text-to-speech model fine-tuned from Microsoft SpeechT5, capable of generating natural speech

Lightweight text-to-speech model trained on 45,000 hours of audio data, capable of controlling voice attributes through text prompts

Parler-TTS Mini: Expresso is a lightweight text-to-speech model fine-tuned on the Expresso dataset based on Parler-TTS Mini v0.1, supporting emotion and speaker control.

A text-to-speech model fine-tuned on the VoxPopuli French dataset based on microsoft/speecht5_tts