Results for “voice-changer”

Transcribe audio files to text with optional speaker diarization and known-speaker hints using OpenAI models.

当需要为特定挑战或目标进行心态和角色转换时

Write natural, subtext-rich dialogue that sounds distinct per character.

Orchestrate altering an existing, working feature to new desired behavior by updating tests first, then changing implementation, reviewing, and committing with gated approval.

Write content in another person's voice with style matching and tone consistency. TRIGGERS - Use when user needs help with ghostwriter related tasks.

Start voice calls via the Clawdbot voice-call plugin.

Creates a presenter-mode deck with speaker notes, theme switching, and a popup teleprompter.

Start voice calls via the OpenClaw voice-call plugin.

Text-to-speech and speech-to-text using fal.ai audio models

Transcribe audio files using Qwen ASR. Use when the user sends voice messages and wants them converted to text.

用自然语言描述生成目标音频。把一段场景描述（人声对话、环境声、音效、背景音乐等复合音频）一次性生成成音频。当用户描述一个声音场景、要求生成/合成/制作一段音频或声音、给出形如"角色：台词"的对话脚本要转成音频、或要按参考音频的音色说话时使用。支持两种模式：纯文本描述生成（T2A）和带参考音频生成（A2A，在描述中引用参考音频指定角色音色）

Text-to-speech and speech-to-text using fal.ai audio models

Voice Agents

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Use when a draft needs the writer's voice and style principles applied

Text-to-speech and speech-to-text using fal.ai audio models

Repurpose one piece of content across six formats while maintaining brand voice

unslop

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

Packages an existing talking-head, interview, or podcast video with timed, designed graphic overlay cards—kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture—synced to the transcript, on a 16:9, 9:16, or 4:5 canvas.