Alternatives to ComfyUI VoxCPM

Open-source desktop studio for voice cloning, voice design, dubbing, dictation and audiobooks — runs on your own machine.

Tokenizer-free open-source TTS by OpenBMB: 30 languages, Voice Design, and 48kHz voice cloning you run on your own GPU.

Fish Audio turns text into expressive, emotionally controllable speech with voice cloning from 15 seconds of audio and a free developer TTS API.

Open-source text-to-speech with fine-grained emotion and prosody control

AI voice cloning and text-to-speech with 140+ languages, emotion control, and lip-sync dubbing for creators and developers.

Fish Audio S2.1 Pro is a real-time text-to-speech and voice cloning platform built around emotion-tag control and a free API tier for developers.

Low-latency text-to-speech API and AI voice agents — Murf AI runs real-time phone conversations at 1 cent per minute.

Real-time voice AI platform: Sonic-3.6 text-to-speech and Ink-2 speech-to-text models plus Managed Agents for building production voice agents.

Emotionally expressive text-to-speech and speech-to-speech voice AI with human-judged evaluation built in.

CAMB.AI is a localization platform for AI dubbing, text-to-speech and live voice translation across 150+ languages.

AIAI.com bundles text-to-image, video, voice-cloning, music, and study tools behind one credit-based subscription.

Open-source Manim plugin that adds voiceovers and word-synced animations directly in Python.

AI voice cloning from a 3-second sample, turned into downloadable MP3 or WAV speech.

Hume OCTAVE is a speech-language model that turns a text description or a 5-second clip into a full voice and personality for real-time voice agents.

Luvvoice is a free text-to-speech tool that turns your text, PDFs, and TXT files into downloadable MP3 narration in 200+ voices across 70+ languages.

ElevenLabs turns text into ultra-realistic AI voice, music, dubbing and conversational voice agents from one credit pool.

Real-time speech AI that rewrites how you sound mid-call — accent, language, clarity — in your own voice

Discontinued: Coqui's hosted Studio and API went offline on December 11, 2023, and the company closed in January 2024. The open-source TTS/XTTS code remains.

VMEG translates, dubs, and lip-syncs video into 170+ languages with 17,000+ premium voices and voice cloning.

AI voice generator with 1,000+ lifelike voices in 60+ languages, plus dubbing, cloning, avatars, and captions

Browser-based cloud that runs 20+ pre-installed open-source AI apps for image, video, and audio generation

Celebrity and character AI voice generation plus lip-synced video, with zero-shot voice cloning now in beta.

AI voice and text-to-song generator for making vocals and full tracks fast.

OpenVoice clones any voice from a 10-second clip, with independent control over emotion, accent, rhythm, and intonation.

Realtime TTS API with sub-100ms latency, instant voice cloning from 5–15 seconds of audio, and 200+ languages.

AI video, music, and text to speech generation from one prompt-driven browser studio.

Browser-based AI dubbing, subtitles and text-to-speech across 30+ languages, with an API for developers.

Speaktor turns text, Word, PDF, and TXT files into MP3, WAV, or SRT narration in 55+ languages at a fraction of premium TTS per-minute rates.

Inworld is a research lab and inference provider for realtime voice AI, offering first-party TTS-2 and STT models plus a zero-markup LLM router for developers

Discontinued: Play.ht (PlayAI) shut down at the end of 2025 after Meta acquired its team in July 2025. Voices and accounts were not migrated.