Suara, musik, dan efek: dalam satu panel.

OpenAI's steerable speech model: ten natural voices you can direct with free-text instructions for tone, accent and pacing.

Google's most expressive Gemini speech model, for long-form narration and two-speaker scenes in 130 languages, with inline vocal cues such as sighs and laughs.

A faster, lower-cost Gemini speech model for high-volume narration and voice agents in 101 languages, with the same voices and vocal cues as 3.8 Flash TTS.

xAI's expressive text-to-speech model with multiple voices and 20-language support.

Google's music model for full-length songs with structure, vocals or instrumentals, guided by a text prompt, optional lyrics and reference images.

Enhanced Lyria model with improved musical coherence and audio quality.

Google's professional-grade music model with enhanced fidelity and musical expression.

ElevenLabs' most expressive speech model, with closer voice cloning, audio tags for delivery and more than 90 languages.

The low-latency tier of ElevenLabs v4, with the same audio tags and more than 90 languages at half the per-character price.

ElevenLabs' most expressive voice model with rich emotional and tonal range.

A variant of ElevenLabs' v3 voice model tuned for natural dialogue in conversational agents, in more than 70 languages.

ElevenLabs music generation model for creating original AI-composed tracks.

MiniMax music model for full-arrangement AI compositions with rich instrumentation.

Mirelo sound effects model for generating custom audio SFX from text prompts.

MiniMax's studio-grade speech model with 332 voices, emotion control, voice cloning, and a 50,000-character input limit.

Fish Audio's text-to-speech model for directed voice performances: you describe how each line should be delivered in square brackets, add sounds and pauses, and script several speakers in one call.

HeyGen's text-to-speech model with preset voices on OpenRouter and Runware; on Runware it can also clone a voice from a recording.

A lower-latency version of HeyGen Voice with the same preset voices on OpenRouter and Runware, and voice cloning on Runware.

Mistral's text-to-speech model with preset voices in eight languages; emotion and pace tags written into the text, such as [emotion=happy] or [pace=slow], direct the delivery. In public preview.

Fish Audio's recommended production TTS with natural-language cues in brackets, multi-speaker synthesis in one call, and zero-shot voice cloning across 83 languages.

Fish Audio's S2.1 Pro model at $0 for development and testing under fair-use limits, with the same bracket cues, multi-speaker synthesis and voice cloning but no latency or data-processing guarantees.

Fish Audio's previous-generation open S2 TTS with natural-language cues in brackets, multi-speaker dialogue and zero-shot voice cloning across 80+ languages.

ByteDance's audio generation model that reads a script word for word or builds a whole scene from one prompt, with a described voice, ambience, music and sound effects, and clones a voice from short reference clips.

Microsoft AI's highest-fidelity text-to-speech model, with detailed prosody and a consistent speaker over long passages. It reads in 23 languages through preset voices across 28 locales, and the voice you pick sets the language.

Microsoft AI's low-latency text-to-speech model, built for real-time responsiveness. It reads in 23 languages through the same preset voices as MAI-Voice-2.1, across 28 locales, and the voice you pick sets the language.

Open full-track music generation with lyric editing, remix, cover generation, and voice cloning in 50+ languages.

ElevenLabs' fastest speech model, with about 75 ms latency across 32 languages at half the per-character price of Multilingual v2.

ElevenLabs' previous-generation voice model for lifelike, consistent long-form narration such as voice-overs and audiobooks, in 29 languages.

ElevenLabs' English-only speech model with very low latency, suited to conversational and real-time use.

ElevenLabs' newest text-to-sound-effects model: foley, ambiences and impacts up to 30 seconds that follow several cues in one prompt, handle music and vocals, and loop seamlessly.

OpenAI's high-accuracy transcription model for recorded audio, which follows a hint for names and terms and returns plain text without timestamps.

OpenAI's open-weight Whisper Large V3, which transcribes speech in close to a hundred languages and returns timed segments for subtitles.

A faster, slimmed-down Whisper Large V3 that keeps most of its accuracy and returns timed segments for subtitles.

Fish Audio's speech-to-text model for multi-speaker conversations, which labels who is speaking and keeps emotion and vocal-event cues such as laughter in the transcript.

Meta's speech-to-text model for push-to-talk and speaker-aware transcription, which returns plain text.

Microsoft AI's multilingual transcription model, which covers 60 languages with automatic language detection and returns plain text.

Mistral's flagship transcription model, which returns a timestamped transcript and detects the language on its own. In public preview.

Mistral's compact transcription model, a lower-cost sibling of Voxtral Small Transcribe 3 with timestamps and language detection. In public preview.

AssemblyAI's speech-to-text model and the successor to Universal-3.5 Pro, served through its synchronous API for clips of up to two minutes. The app sends a longer recording in two-minute pieces and returns plain text.

AssemblyAI's text-to-speech model for voice agents, narration and multilingual applications, with twenty preset voices here in English, Spanish, French and German.

Google's speech-to-text model for fast synchronous transcription with automatic language detection; this route returns plain text.

ElevenLabs' batch transcription model, which returns word-level timing for subtitles and can label who is speaking.

ElevenLabs' batch transcription model tuned for clinical and medical terminology, which returns word-level timing for subtitles and can label who is speaking.

Kuaishou's Kling sound effects model, generating 3 to 10 second clips from a short text description.

Kuaishou's Kling text-to-speech model, reading up to 1,000 characters aloud in English or Chinese system voices.

Gradium's 31M-parameter English text-to-speech model, run on device by Ollama on Apple silicon Macs. It reads text as written, so numbers and dates are best spelled out.

Liquid AI's 2B audio model, run on device by Ollama: it speaks text in 19 languages with a female or male voice per language, and transcribes speech.

On-device English text-to-speech that runs entirely in the app, with ten preset voices and no API key.

A small on-device Whisper model that transcribes speech in the app with no API key, trading accuracy for speed.

A mid-sized on-device Whisper model that transcribes speech in the app with no API key, balancing speed and accuracy.