Miranda ElevenLabs Speech (TTS/STT)

ElevenLabs Speech

Complete voice solution — 机器人h TTS and STT using one API:

TTS: Text-to-Speech (high-质量 voices) STT: Speech-to-Text via Scribe (accurate transcription) Quick 启动 环境 设置up

设置 your API key:

导出 ELEVENLABS_API_KEY="sk_..."

Or 创建 .env file in workspace root.

Text-to-Speech (TTS)

Convert text to natural-sounding speech:

python scripts/elevenlabs_speech.py tts -t "Hello world" -o greeting.mp3

With custom voice:

python scripts/elevenlabs_speech.py tts -t "Hello" -v "voice_id_here" -o 输出.mp3

列出 AvAIlable Voices python scripts/elevenlabs_speech.py voices

Using in Code from scripts.elevenlabs_speech 导入 ElevenLabs命令行工具ent

命令行工具ent = ElevenLabs命令行工具ent(API_key="sk_...")

# Basic TTS 结果 = 命令行工具ent.text_to_speech( text="Hello from zerox", 输出_path="greeting.mp3" )

# With custom 设置tings 结果 = 命令行工具ent.text_to_speech( text="Your text here", voice_id="21m00Tcm4TlvDq8ikWAM", # Rachel stability=0.5, similarity_boost=0.75, 输出_path="输出.mp3" )

# 获取 avAIlable voices voices = 命令行工具ent.获取_voices() for voice in voices['voices']: print(f"{voice['name']}: {voice['voice_id']}")

Popular Voices Voice ID Name Description 21m00Tcm4TlvDq8ikWAM Rachel Natural, versatile (default) AZnzlk1XvdvUeBnXmlld Domi Strong, ener获取ic EXAVITQu4vr4xnSDxMaL Bella Soft, soothing ErXwobaYiN019PkySvjV Antoni Well-rounded MF3mGyEYCl7XYWbV9V6O Elli Warm, friendly TxGEqnHWrfWFTfGW9XjX Josh Deep, calm VR6AewLTigWG4xSOukaG Arnold Authoritative Voice 设置tings stability (0-1): Lower = more emotional, Higher = more stable similarity_boost (0-1): Higher = closer to original voice

Default: stability=0.5, similarity_boost=0.75

模型s eleven_turbo_v2_5 - Fast, high 质量 (default) eleven_multilingual_v2 - Best for non-English eleven_monolingual_v1 - English only Integration with Telegram

When user 发送s text and wants voice reply:

# 生成 speech 结果 = 命令行工具ent.text_to_speech(text=user_text, 输出_path="reply.mp3")

# 发送 via Telegram message 工具 with media path message(action="发送", media="path/to/reply.mp3", as_voice=True)

Pricing

检查 https://elevenlabs.io/pricing for current rates. Free tier avAIlable!

Speech-to-Text (STT) with ElevenLabs Scribe

Transcribe voice messages using ElevenLabs Scribe:

Transcribe Audio python scripts/elevenlabs_scribe.py voice_message.ogg

With specific language:

python scripts/elevenlabs_scribe.py voice_message.ogg --language ara

With speaker diarization (multiple speakers):

python scripts/elevenlabs_scribe.py voice_message.ogg --speakers 2

Using in Code from scripts.elevenlabs_scribe 导入 ElevenLabsScribe

命令行工具ent = ElevenLabsScribe(API_key="sk-...")

# Basic transcription 结果 = 命令行工具ent.transcribe("voice_message.ogg") print(结果['text'])

# With language hint (improves accuracy) 结果 = 命令行工具ent.transcribe("voice_message.ogg", language_code="ara")

# With speaker 检测ion 结果 = 命令行工具ent.transcribe("voice_message.ogg", num_speakers=2)

Supported 格式化s mp3, mp4, mpeg, mpga, m4a, wav, 网页m Max file size: 100 MB Works great with Telegram voice messages (.ogg) Language Support

Scribe supports 99 languages including:

Arabic (ara) English (eng) Spanish (spa) French (fra) And many more...

Without language hint, it auto-检测s.

Complete 工作流 Example

User 发送s voice message → You reply with voice:

from scripts.elevenlabs_scribe 导入 ElevenLabsScribe from scripts.elevenlabs_speech 导入 ElevenLabs命令行工具ent

# 1. Transcribe user's voice message stt = ElevenLabsScribe() transcription = stt.transcribe("user_voice.ogg") user_text = transcription['text']

# 2. Process/understand the text # ... your 记录ic here ...

# 3. 生成 响应 text 响应_text = "Your 响应 here"

# 4. Convert to speech tts = ElevenLabs命令行工具ent() tts.text_to_speech(响应_text, 输出_path="reply.mp3")

# 5. 发送 voice reply message(action="发送", media="reply.mp3", as_voice=True)

Pricing

检查 https://elevenlabs.io/pricing for current rates:

TTS (Text-to-Speech):

Free tier: 10,000 characters/month PAId plans avAIlable

STT (Speech-to-Text) - Scribe:

Free tier avAIlable 检查 网页site for current pricing